Markdown Vault MCP

claude mcp add markdown-vault-mcp -e 'MARKDOWN_VAULT_MCP_KV_STORE_URL=file:///data/state' -e 'MARKDOWN_VAULT_MCP_TOOLS_ALLOW=<MARKDOWN_VAULT_MCP_TOOLS_ALLOW>' -e 'MARKDOWN_VAULT_MCP_TOOLS_DENY=<MARKDOWN_VAULT_MCP_TOOLS_DENY>' -e 'MARKDOWN_VAULT_MCP_SERVER_NAME=<MARKDOWN_VAULT_MCP_SERVER_NAME>' -e 'MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION=<MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION>' -e 'MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA=<MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA>' -e 'MARKDOWN_VAULT_MCP_INSTRUCTIONS=<MARKDOWN_VAULT_MCP_INSTRUCTIONS>' -e 'MARKDOWN_VAULT_MCP_LOG_LEVEL=INFO' -e 'MARKDOWN_VAULT_MCP_LOG_FORMAT=<MARKDOWN_VAULT_MCP_LOG_FORMAT>' -e 'OLLAMA_HOST=http://localhost:11434' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'VOYAGE_API_KEY=<your voyage_api_key>' -e 'OPENAI_BASE_URL=<OPENAI_BASE_URL>' -e 'OPENAI_EMBEDDING_MODEL=<OPENAI_EMBEDDING_MODEL>' -e 'MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S=60' -e 'MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S=60' -e 'MARKDOWN_VAULT_MCP_SOURCE_DIR=/data/vault' -e 'MARKDOWN_VAULT_MCP_READ_ONLY=false' -e 'MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING=true' -e 'MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS=false' -e 'MARKDOWN_VAULT_MCP_DISABLE_APPS_UI=false' -e 'MARKDOWN_VAULT_MCP_INDEX_PATH=<MARKDOWN_VAULT_MCP_INDEX_PATH>' -e 'MARKDOWN_VAULT_MCP_STATE_PATH=<MARKDOWN_VAULT_MCP_STATE_PATH>' -e 'MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH=<MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH>' -e 'MARKDOWN_VAULT_MCP_INDEXED_FIELDS=<MARKDOWN_VAULT_MCP_INDEXED_FIELDS>' -e 'MARKDOWN_VAULT_MCP_REQUIRED_FIELDS=<MARKDOWN_VAULT_MCP_REQUIRED_FIELDS>' -e 'MARKDOWN_VAULT_MCP_EXCLUDE=<MARKDOWN_VAULT_MCP_EXCLUDE>' -e 'MARKDOWN_VAULT_MCP_TITLE_FIELD=title' -e 'MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS=<MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS>' -e 'MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER=_templates' -e 'MARKDOWN_VAULT_MCP_PROMPTS_FOLDER=<MARKDOWN_VAULT_MCP_PROMPTS_FOLDER>' -e 'MARKDOWN_VAULT_MCP_CONVENTIONS_FILE=_conventions.md' -e 'MARKDOWN_VAULT_MCP_OKF_MODE=auto' -e 'MARKDOWN_VAULT_MCP_OKF_WRITE=false' -e 'MARKDOWN_VAULT_MCP_OKF_VERIFY=elicit' -e 'MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS=<MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS>' -e 'MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB=1.0' -e 'MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES=262144' -e 'MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE=auto' -e 'MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE=2' -e 'MARKDOWN_VAULT_MCP_SNIPPET_WORDS=200' -e 'MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA=0.25' -e 'MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS=400' -e 'MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS=<MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS>' -e 'MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS=40' -e 'MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS=<MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS>' -e 'MARKDOWN_VAULT_MCP_FTS_WEIGHTS=<MARKDOWN_VAULT_MCP_FTS_WEIGHTS>' -e 'MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=<MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER>' -e 'MARKDOWN_VAULT_MCP_OLLAMA_MODEL=nomic-embed-text' -e 'MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY=false' -e 'MARKDOWN_VAULT_MCP_VOYAGE_MODEL=voyage-4' -e 'MARKDOWN_VAULT_MCP_OPENAI_BASE_URL=https://api.openai.com/v1' -e 'MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL=text-embedding-3-small' -e 'MARKDOWN_VAULT_MCP_FASTEMBED_MODEL=BAAI/bge-small-en-v1.5' -e 'MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR=<MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR>' -e 'MARKDOWN_VAULT_MCP_EMBED_CONTEXT=false' -e 'MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S=30.0' -e 'MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE=4' -e 'MARKDOWN_VAULT_MCP_GIT_TOKEN=<your markdown_vault_mcp_git_token>' -e 'MARKDOWN_VAULT_MCP_GIT_REPO_URL=<MARKDOWN_VAULT_MCP_GIT_REPO_URL>' -e 'MARKDOWN_VAULT_MCP_GIT_USERNAME=x-access-token' -e 'MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S=600' -e 'MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S=30.0' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME=markdown-vault-mcp' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL=noreply@markdown-vault-mcp' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM=<MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM>' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM=<MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM>' -e 'MARKDOWN_VAULT_MCP_GIT_LFS=true' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER=true' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S=2.0' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR=true' -e 'MARKDOWN_VAULT_MCP_BOOT_REINDEX=true' -e 'MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET=<your markdown_vault_mcp_github_webhook_secret>' -e 'MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN=<your markdown_vault_mcp_gitlab_webhook_signing_token>' -e 'MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN=<your markdown_vault_mcp_gitlab_webhook_secret_token>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER=<MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY=<your markdown_vault_mcp_summarize_openai_api_key>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL=<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL=gpt-5-mini' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS=8192' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES=50' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS=200000' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT=120.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S=3600.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S=86400.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S=60.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S=60.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES=104857600' -e 'MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S=25.0' -e 'MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S=3600.0' -e 'MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT=256' -- uvx markdown-vault-mcp==5.1.0

{
    "mcpServers": {
        "markdown-vault-mcp": {
            "command": "uvx",
            "args": [
                "markdown-vault-mcp==5.1.0"
            ],
            "env": {
                "MARKDOWN_VAULT_MCP_KV_STORE_URL": "file:///data/state",
                "MARKDOWN_VAULT_MCP_TOOLS_ALLOW": "<MARKDOWN_VAULT_MCP_TOOLS_ALLOW>",
                "MARKDOWN_VAULT_MCP_TOOLS_DENY": "<MARKDOWN_VAULT_MCP_TOOLS_DENY>",
                "MARKDOWN_VAULT_MCP_SERVER_NAME": "<MARKDOWN_VAULT_MCP_SERVER_NAME>",
                "MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION": "<MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION>",
                "MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA": "<MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA>",
                "MARKDOWN_VAULT_MCP_INSTRUCTIONS": "<MARKDOWN_VAULT_MCP_INSTRUCTIONS>",
                "MARKDOWN_VAULT_MCP_LOG_LEVEL": "INFO",
                "MARKDOWN_VAULT_MCP_LOG_FORMAT": "<MARKDOWN_VAULT_MCP_LOG_FORMAT>",
                "OLLAMA_HOST": "http://localhost:11434",
                "OPENAI_API_KEY": "<your openai_api_key>",
                "VOYAGE_API_KEY": "<your voyage_api_key>",
                "OPENAI_BASE_URL": "<OPENAI_BASE_URL>",
                "OPENAI_EMBEDDING_MODEL": "<OPENAI_EMBEDDING_MODEL>",
                "MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S": "60",
                "MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S": "60",
                "MARKDOWN_VAULT_MCP_SOURCE_DIR": "/data/vault",
                "MARKDOWN_VAULT_MCP_READ_ONLY": "false",
                "MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING": "true",
                "MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS": "false",
                "MARKDOWN_VAULT_MCP_DISABLE_APPS_UI": "false",
                "MARKDOWN_VAULT_MCP_INDEX_PATH": "<MARKDOWN_VAULT_MCP_INDEX_PATH>",
                "MARKDOWN_VAULT_MCP_STATE_PATH": "<MARKDOWN_VAULT_MCP_STATE_PATH>",
                "MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH": "<MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH>",
                "MARKDOWN_VAULT_MCP_INDEXED_FIELDS": "<MARKDOWN_VAULT_MCP_INDEXED_FIELDS>",
                "MARKDOWN_VAULT_MCP_REQUIRED_FIELDS": "<MARKDOWN_VAULT_MCP_REQUIRED_FIELDS>",
                "MARKDOWN_VAULT_MCP_EXCLUDE": "<MARKDOWN_VAULT_MCP_EXCLUDE>",
                "MARKDOWN_VAULT_MCP_TITLE_FIELD": "title",
                "MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS": "<MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS>",
                "MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER": "_templates",
                "MARKDOWN_VAULT_MCP_PROMPTS_FOLDER": "<MARKDOWN_VAULT_MCP_PROMPTS_FOLDER>",
                "MARKDOWN_VAULT_MCP_CONVENTIONS_FILE": "_conventions.md",
                "MARKDOWN_VAULT_MCP_OKF_MODE": "auto",
                "MARKDOWN_VAULT_MCP_OKF_WRITE": "false",
                "MARKDOWN_VAULT_MCP_OKF_VERIFY": "elicit",
                "MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS": "<MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS>",
                "MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB": "1.0",
                "MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES": "262144",
                "MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE": "auto",
                "MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE": "2",
                "MARKDOWN_VAULT_MCP_SNIPPET_WORDS": "200",
                "MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA": "0.25",
                "MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS": "400",
                "MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS": "<MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS>",
                "MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS": "40",
                "MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS": "<MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS>",
                "MARKDOWN_VAULT_MCP_FTS_WEIGHTS": "<MARKDOWN_VAULT_MCP_FTS_WEIGHTS>",
                "MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER": "<MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER>",
                "MARKDOWN_VAULT_MCP_OLLAMA_MODEL": "nomic-embed-text",
                "MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY": "false",
                "MARKDOWN_VAULT_MCP_VOYAGE_MODEL": "voyage-4",
                "MARKDOWN_VAULT_MCP_OPENAI_BASE_URL": "https://api.openai.com/v1",
                "MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL": "text-embedding-3-small",
                "MARKDOWN_VAULT_MCP_FASTEMBED_MODEL": "BAAI/bge-small-en-v1.5",
                "MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR": "<MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR>",
                "MARKDOWN_VAULT_MCP_EMBED_CONTEXT": "false",
                "MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S": "30.0",
                "MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE": "4",
                "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<your markdown_vault_mcp_git_token>",
                "MARKDOWN_VAULT_MCP_GIT_REPO_URL": "<MARKDOWN_VAULT_MCP_GIT_REPO_URL>",
                "MARKDOWN_VAULT_MCP_GIT_USERNAME": "x-access-token",
                "MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S": "600",
                "MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S": "30.0",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME": "markdown-vault-mcp",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL": "noreply@markdown-vault-mcp",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM": "<MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM>",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM": "<MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM>",
                "MARKDOWN_VAULT_MCP_GIT_LFS": "true",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER": "true",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S": "2.0",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR": "true",
                "MARKDOWN_VAULT_MCP_BOOT_REINDEX": "true",
                "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<your markdown_vault_mcp_github_webhook_secret>",
                "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<your markdown_vault_mcp_gitlab_webhook_signing_token>",
                "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<your markdown_vault_mcp_gitlab_webhook_secret_token>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER": "<MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<your markdown_vault_mcp_summarize_openai_api_key>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL": "gpt-5-mini",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS": "8192",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES": "50",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS": "200000",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT": "120.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S": "3600.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S": "86400.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S": "60.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S": "60.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES": "104857600",
                "MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S": "25.0",
                "MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S": "3600.0",
                "MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT": "256"
            }
        }
    }
}

Variables d'environnement

• MARKDOWN_VAULT_MCP_KV_STORE_URL Persistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` (with a warning) on a host where that directory is not usable.
• MARKDOWN_VAULT_MCP_TOOLS_ALLOW Comma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`.
• MARKDOWN_VAULT_MCP_TOOLS_DENY Comma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`.
• MARKDOWN_VAULT_MCP_SERVER_NAME Rename this server instance; defaults to the project name.
• MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION Concise routing context that distinguishes this deployment's material or responsibility.
• MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA Deployment-specific behavioral policy added to the generated MCP instructions.
• MARKDOWN_VAULT_MCP_INSTRUCTIONS Legacy: replaces all generated MCP instructions (deprecated; use _INSTANCE_DESCRIPTION for routing and _INSTRUCTIONS_EXTRA for policy).
• MARKDOWN_VAULT_MCP_LOG_LEVEL Log level for every logger in the process, FastMCP's included (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. The unprefixed FASTMCP_LOG_LEVEL still works for one major version and logs a deprecation warning.
• MARKDOWN_VAULT_MCP_LOG_FORMAT Log rendering. rich is one colour event key=value line per record, for a terminal; json is one JSON object per record, for a collector. Unset picks rich when stderr is a terminal and json everywhere else, so a container or journald gets JSON with no configuration.
• OLLAMA_HOST Ollama server URL for the ollama embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the Ollama ecosystem convention.
• OPENAI_API_KEY secret OpenAI API key for the openai embedding provider, and the fallback key for the summarize tool when MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY is unset. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OpenAI ecosystem convention.
• VOYAGE_API_KEY secret Voyage AI API key for the voyage embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OPENAI_API_KEY / OLLAMA_HOST convention. Setting it never auto-selects the provider; choose it explicitly with MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=voyage.
• OPENAI_BASE_URL Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_BASE_URL (embeddings). For the summarize tool it only routes traffic when an API key already enables the feature; it never enables summarize by itself.
• OPENAI_EMBEDDING_MODEL Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL.
• MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S Maximum seconds an index-backed tool or resource waits for the FTS index to become queryable during a cold-start background build before raising IndexUnavailableError(reason="timeout"). Increase for large vaults.
• MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S Maximum seconds an index-querying read tool waits for the IndexWriter to drain when called with wait_for_pending_writes=true. On timeout the tool answers from the current index and reports index_stale=true in the response _meta.
• MARKDOWN_VAULT_MCP_SOURCE_DIR Path to the markdown vault directory. When it does not exist, or the server cannot access it, the server starts but every tool fails with a message saying which until it is fixed (managed git mode clones into it). Symbolic links inside the vault are followed on Python 3.13+.
• MARKDOWN_VAULT_MCP_READ_ONLY Set to true to hide the write tools (write, edit, append, delete, rename, move_folder, fetch, git_sync, the okf_* tools, create_upload_link) and serve a search-only vault.
• MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING Refuse a write that would overwrite an existing file when no if_match etag is supplied. Deliberate replacement still works: read the file first, then pass if_match. Unaffected: edit, append, delete, rename. Set to false to allow blind overwrites.
• MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS Set to true to have write, edit and append list, under unresolved_links, the target of each link the call added that get_broken_links reports. Links the note already held are left out. Off by default, leaving those responses unchanged.
• MARKDOWN_VAULT_MCP_DISABLE_APPS_UI Hide the MCP Apps UI tools (browse_vault, show_context) from the tool listing for clients that do not render MCP Apps panels.
• MARKDOWN_VAULT_MCP_INDEX_PATH Path to the SQLite FTS5 index file; unset keeps the index in memory. Set it for persistence across restarts.
• MARKDOWN_VAULT_MCP_STATE_PATH Path to the change-tracking state file. Defaults to INDEX_PATH plus .state.json (index.db.state.json beside index.db); without INDEX_PATH the state is kept in memory. Never written into the vault by default.
• MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH Base path for the embeddings files. Defaults beside INDEX_PATH (index-db-embeddings.npy and .json beside index.db); without INDEX_PATH the vectors are kept in memory and rebuilt at each start. Setting it also lets the provider be auto-detected.
• MARKDOWN_VAULT_MCP_INDEXED_FIELDS Comma-separated frontmatter fields promoted to the tag index for structured filtering. Changing it cold-rebuilds the index once on next startup; SEARCHABLE_FIELDS inherits this value when unset.
• MARKDOWN_VAULT_MCP_REQUIRED_FIELDS Comma-separated frontmatter fields required on every document; documents missing any are excluded from the index.
• MARKDOWN_VAULT_MCP_EXCLUDE Comma-separated glob patterns excluded from scanning, e.g. .obsidian/**,.trash/**.
• MARKDOWN_VAULT_MCP_TITLE_FIELD Frontmatter field used as the document title (falls back to title, the first H1, then the filename). Changing it cold-rebuilds the index once on next startup.
• MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS Comma-separated frontmatter fields whose text values become keyword-searchable and enrich first-chunk embeddings. Inherits INDEXED_FIELDS when unset; the sentinel none means filterable but not searchable. Changing it cold-rebuilds the index and re-embeds once on next startup.
• MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER Relative folder where note templates live (used by the create_from_template prompt).
• MARKDOWN_VAULT_MCP_PROMPTS_FOLDER Directory of .md prompt files that extend or override built-in prompts; a relative path is resolved against SOURCE_DIR.
• MARKDOWN_VAULT_MCP_CONVENTIONS_FILE Filename of the per-folder conventions files surfaced to clients at write time (bare .md filename without glob characters). Set to none to disable folder conventions.
• MARKDOWN_VAULT_MCP_OKF_MODE OKF (Open Knowledge Format) read semantics. With auto (the default), read annotations switch on when the vault declares an OKF version in its root index.md. Use off to disable OKF semantics entirely, or on to force them for an undeclared vault. Annotations are read-only; write behavior is never affected.
• MARKDOWN_VAULT_MCP_OKF_WRITE OKF (Open Knowledge Format) enforced write layer. When true on an OKF-active vault, the server stamps generated provenance on each write and clears any verified attestation when a note's content changes. It also keeps each written folder's log.md and index.md current, and exposes the okf_verify tool. Requires OKF_MODE to be auto or on (a true value with OKF_MODE=off is a config error). Off by default.
• MARKDOWN_VAULT_MCP_OKF_VERIFY How the okf_verify tool attributes a human review. This applies only when OKF_WRITE is on, which gates the tool. With elicit (the default), okf_verify asks the human to confirm the review through an MCP elicitation, then records the attestation only on an affirmative reply. It fails closed when the client cannot elicit or the human declines, so a model holding the human's token cannot self-attest. Set trust-auth instead to attribute to a token's sub claim with no confirmation; it rejects static bearer credentials and other client-ID-only identities. This is safe only when the sole caller is a human-driven UI. Set off to hide the tool, leaving attestation to external tooling. A non-default value with OKF_WRITE off is a config error.
• MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS Comma-separated allowed attachment extensions (e.g. pdf,png,jpg); case and a leading dot are ignored, so PDF and .pdf name the same type. Use * to allow every non-markdown file. Unset selects the built-in allowlist. A link whose target has a listed extension is not part of the link graph; changing the list rebuilds the index once.
• MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB Maximum attachment size in MB returned by read / accepted by write; 0 disables the limit.
• MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES Maximum bytes returned by a full-document read of a note; use `read(path, section=…)` for partial reads. 0 disables the limit.
• MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE Mode used when a search call omits 'mode': auto, keyword, semantic, or hybrid. The default 'auto' picks hybrid when embeddings are configured and keyword when they are not. Pin 'keyword' to keep unqualified searches off the embedding provider (each hybrid or semantic search embeds the query, which costs an API call on a metered provider). A configured semantic/hybrid default also degrades to keyword without embeddings, so no setting can make a vault unsearchable; an explicit mode= argument is never downgraded.
• MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE Maximum chunks returned per document in search results.
• MARKDOWN_VAULT_MCP_SNIPPET_WORDS Width of the snippet window (words) in search results; 0 returns full chunk content.
• MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA Down-weights longer chunks in ranking: score / (1 + alpha * log(chunk_count)).
• MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS Word cap per chunk; the adaptive chunker splits at deeper heading levels, then paragraph/word boundaries, to respect it. Match it to the embedding model's context. A reindex applies a new value.
• MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS Character cap enforced alongside MAX_CHUNK_WORDS to bound token-dense chunks. Unset derives min(1500, model context * 2.8). Set a positive value for an exact cap, or -1 to scale with the model's full context (can exhaust memory on long-context models). A reindex applies a new value.
• MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS Words of overlap between adjacent budget-split fragments of the same heading section (0 disables). A reindex applies a new value.
• MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS Folder-prefix score multipliers (`prefix:weight` pairs, comma-separated, weights > 0) applied to all search modes; the deepest matching prefix wins (sessions:0.5 demotes sessions/**).
• MARKDOWN_VAULT_MCP_FTS_WEIGHTS Per-column BM25 weights (`column:weight` pairs, comma-separated, weights >= 0) for keyword ranking. Columns: path, title, folder, heading, content, summary.
• MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER Embedding provider: openai, voyage, ollama, or fastembed; setting it turns on search by meaning. Unset auto-detects from the environment (never voyage), but only when EMBEDDINGS_PATH is set. Any OpenAI-compatible endpoint works with openai plus OPENAI_BASE_URL; see the embeddings guide.
• MARKDOWN_VAULT_MCP_OLLAMA_MODEL Ollama embedding model name.
• MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY Force Ollama to embed on CPU only.
• MARKDOWN_VAULT_MCP_VOYAGE_MODEL Voyage AI embedding model name.
• MARKDOWN_VAULT_MCP_OPENAI_BASE_URL OpenAI-compatible API base URL for embeddings; the bare OPENAI_BASE_URL is honoured as a fallback.
• MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL OpenAI-compatible embedding model name; the bare OPENAI_EMBEDDING_MODEL is honoured as a fallback.
• MARKDOWN_VAULT_MCP_FASTEMBED_MODEL FastEmbed model name.
• MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR FastEmbed model cache directory (in Docker, stored under /data/state/fastembed).
• MARKDOWN_VAULT_MCP_EMBED_CONTEXT Enrich embedding input with the note title, chunk heading, and (first chunk) searchable-field values. Flipping it re-embeds the whole vault once on next startup.
• MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S Per-request wall-clock budget in seconds for a single embedding HTTP call (OpenAI/Ollama). The local FastEmbed backend runs in-process with no network call and ignores this. CPU-only or large-model workloads may need 60-120 s; raise this if batches time out.
• MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE Number of chunks sent per embedding request. Smaller batches shorten each request (useful under a tight timeout on slow models) at the cost of more round-trips.
• MARKDOWN_VAULT_MCP_GIT_TOKEN secret Token/password for HTTPS git auth; remotes must be HTTPS when set.
• MARKDOWN_VAULT_MCP_GIT_REPO_URL HTTPS remote URL for managed git mode: the server clones into an empty SOURCE_DIR on startup (or validates an existing origin) and enables the pull loop, auto-commit, and deferred push.
• MARKDOWN_VAULT_MCP_GIT_USERNAME Username for HTTPS git auth prompts (x-access-token for GitHub, oauth2 for GitLab, the account name for Bitbucket).
• MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S Seconds between git fetch + fast-forward update attempts; 0 disables periodic pull.
• MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S Seconds of write-idle time before pushing; 0 pushes only on shutdown.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME Git committer name for auto-commits, and the author name too unless an OIDC claim supplies one; set this in Docker where git config user.name is empty.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL Git committer email for auto-commits, and the author email too unless an OIDC claim supplies one.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM OIDC claim key used as the commit author name (e.g. name) when an OIDC token is present; the committer stays GIT_COMMIT_NAME. The claim is resolved when the tool call arrives and carried to the background commit, so it applies on every write. A configured claim the token does not carry is reported once at WARNING and the static identity is used.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM OIDC claim key used as the commit author email (e.g. email) when an OIDC token is present; the committer stays GIT_COMMIT_EMAIL. Resolved and carried the same way as the name claim.
• MARKDOWN_VAULT_MCP_GIT_LFS Run git lfs pull on startup to fetch LFS-tracked attachments; set to false for repos without LFS.
• MARKDOWN_VAULT_MCP_FILE_WATCHER Watch the vault for external filesystem changes; auto-disabled when git pull is active or a webhook can deliver (HTTP/SSE transports only). Requires the file-watcher extra.
• MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S Seconds of quiet after the last filesystem event before reindexing.
• MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR Keep the non-recursive watch on the vault root; set false to register zero source-dir-rooted FSEvents streams (avoids repeated macOS access prompts on a home-rooted vault) at the cost of root-level files relying on scans.
• MARKDOWN_VAULT_MCP_BOOT_REINDEX Reconcile offline changes at startup by reindexing once the initial build completes. Set false on a large vault to start without paying a full filesystem scan per server start; changes made while no server was running are then invisible until a reindex runs (the reindex tool, or 'markdown-vault-mcp reindex'). Note that `index_stale` reports writer idleness, not agreement with disk, so it reads false while the index may still differ from the vault.
• MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET secret Shared secret for the GitHub push-event webhook; when set, mounts POST /github-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events.
• MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN secret Signing token for the GitLab push-event webhook (GitLab 19.0+); when set, mounts POST /gitlab-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. GitLab generates this value; copy the `whsec_` token it shows under Generate signing token rather than inventing one. Deliveries are authenticated by HMAC-SHA256 over the webhook id, timestamp and body, and a delivery older than 5 minutes is rejected.
• MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN secret Secret token for the GitLab push-event webhook, GitLab's plain-text form and the only one below 19.0; also mounts POST /gitlab-webhook. It proves nothing about the body and cannot expire, so prefer the signing token where the GitLab version offers it. Setting both accepts either, which is how an existing webhook migrates.
• MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER Summarization backend (only openai is recognised). Unset auto-detects: the backend activates when credentials or an explicit endpoint are present.
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY secret API key for the OpenAI-compatible summarize endpoint; the bare OPENAI_API_KEY is honoured as a fallback. Unset works for keyless local endpoints (Ollama).
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL OpenAI-compatible endpoint base URL for the summarize tool; setting it enables the tool even without an API key. The bare OPENAI_BASE_URL routes traffic only when a key already enables the feature.
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL Chat model id used for summaries.
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS Upper bound on generated tokens per summarize call; on reasoning models this budget also covers internal reasoning tokens.
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES Cap on the number of notes summarised in one call (subtree expansion truncates to this many).
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS Aggregate cap on note characters sent to the model in one call; excess is truncated with a flag on the result.
• MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT Per-request wall-clock budget in seconds for a single summarize backend call; keep it below the MCP client's request timeout so the server-side error wins the race.
• MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S Link lifetime in seconds when the caller requests no explicit TTL.
• MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S Ceiling in seconds a caller-requested link TTL is clamped to.
• MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.
• MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S Crashed-handler reclaim window in seconds for an in-flight reservation.
• MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES Maximum size in bytes of a single upload.
• MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S Seconds a long-running tool call may run in the foreground before it is promoted to a background job and a job handle is returned instead.
• MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S Seconds a background-job record (working or finished) is retained for polling before it expires from the store.
• MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT Maximum live background jobs per calling subject; further promotions are rejected until older records expire.

claude mcp add markdown-vault-mcp -e 'MARKDOWN_VAULT_MCP_SHUTDOWN_GRACE_S=3' -e 'MARKDOWN_VAULT_MCP_BASE_URL=<MARKDOWN_VAULT_MCP_BASE_URL>' -e 'MARKDOWN_VAULT_MCP_BEARER_TOKEN=<your markdown_vault_mcp_bearer_token>' -e 'MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL=<MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL>' -e 'MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID=<MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID>' -e 'MARKDOWN_VAULT_MCP_OIDC_CLIENT_SECRET=<your markdown_vault_mcp_oidc_client_secret>' -e 'MARKDOWN_VAULT_MCP_OIDC_AUDIENCE=<MARKDOWN_VAULT_MCP_OIDC_AUDIENCE>' -e 'MARKDOWN_VAULT_MCP_OIDC_REQUIRED_SCOPES=openid' -e 'MARKDOWN_VAULT_MCP_OIDC_ADVERTISED_SCOPES=openid offline_access' -e 'MARKDOWN_VAULT_MCP_OIDC_JWT_SIGNING_KEY=<your markdown_vault_mcp_oidc_jwt_signing_key>' -e 'MARKDOWN_VAULT_MCP_OIDC_VERIFY_ACCESS_TOKEN=false' -e 'MARKDOWN_VAULT_MCP_KV_STORE_URL=file:///data/state' -e 'MARKDOWN_VAULT_MCP_APP_DOMAIN=<MARKDOWN_VAULT_MCP_APP_DOMAIN>' -e 'MARKDOWN_VAULT_MCP_TOOLS_ALLOW=<MARKDOWN_VAULT_MCP_TOOLS_ALLOW>' -e 'MARKDOWN_VAULT_MCP_TOOLS_DENY=<MARKDOWN_VAULT_MCP_TOOLS_DENY>' -e 'MARKDOWN_VAULT_MCP_AUTH_MODE=<MARKDOWN_VAULT_MCP_AUTH_MODE>' -e 'MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE=<MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE>' -e 'MARKDOWN_VAULT_MCP_BEARER_DEFAULT_SUBJECT=bearer-anon' -e 'MARKDOWN_VAULT_MCP_SERVER_NAME=<MARKDOWN_VAULT_MCP_SERVER_NAME>' -e 'MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION=<MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION>' -e 'MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA=<MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA>' -e 'MARKDOWN_VAULT_MCP_INSTRUCTIONS=<MARKDOWN_VAULT_MCP_INSTRUCTIONS>' -e 'MARKDOWN_VAULT_MCP_HTTP_PATH=/mcp' -e 'MARKDOWN_VAULT_MCP_HEALTH_DETAIL=standard' -e 'PUID=1000' -e 'PGID=1000' -e 'MARKDOWN_VAULT_MCP_LOG_LEVEL=INFO' -e 'MARKDOWN_VAULT_MCP_LOG_FORMAT=<MARKDOWN_VAULT_MCP_LOG_FORMAT>' -e 'OLLAMA_HOST=http://localhost:11434' -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'VOYAGE_API_KEY=<your voyage_api_key>' -e 'OPENAI_BASE_URL=<OPENAI_BASE_URL>' -e 'OPENAI_EMBEDDING_MODEL=<OPENAI_EMBEDDING_MODEL>' -e 'MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S=60' -e 'MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S=60' -e 'MARKDOWN_VAULT_MCP_SOURCE_DIR=/data/vault' -e 'MARKDOWN_VAULT_MCP_READ_ONLY=false' -e 'MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING=true' -e 'MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS=false' -e 'MARKDOWN_VAULT_MCP_DISABLE_APPS_UI=false' -e 'MARKDOWN_VAULT_MCP_INDEX_PATH=<MARKDOWN_VAULT_MCP_INDEX_PATH>' -e 'MARKDOWN_VAULT_MCP_STATE_PATH=<MARKDOWN_VAULT_MCP_STATE_PATH>' -e 'MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH=<MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH>' -e 'MARKDOWN_VAULT_MCP_INDEXED_FIELDS=<MARKDOWN_VAULT_MCP_INDEXED_FIELDS>' -e 'MARKDOWN_VAULT_MCP_REQUIRED_FIELDS=<MARKDOWN_VAULT_MCP_REQUIRED_FIELDS>' -e 'MARKDOWN_VAULT_MCP_EXCLUDE=<MARKDOWN_VAULT_MCP_EXCLUDE>' -e 'MARKDOWN_VAULT_MCP_TITLE_FIELD=title' -e 'MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS=<MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS>' -e 'MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER=_templates' -e 'MARKDOWN_VAULT_MCP_PROMPTS_FOLDER=<MARKDOWN_VAULT_MCP_PROMPTS_FOLDER>' -e 'MARKDOWN_VAULT_MCP_CONVENTIONS_FILE=_conventions.md' -e 'MARKDOWN_VAULT_MCP_OKF_MODE=auto' -e 'MARKDOWN_VAULT_MCP_OKF_WRITE=false' -e 'MARKDOWN_VAULT_MCP_OKF_VERIFY=elicit' -e 'MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS=<MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS>' -e 'MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB=1.0' -e 'MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES=262144' -e 'MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE=auto' -e 'MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE=2' -e 'MARKDOWN_VAULT_MCP_SNIPPET_WORDS=200' -e 'MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA=0.25' -e 'MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS=400' -e 'MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS=<MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS>' -e 'MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS=40' -e 'MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS=<MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS>' -e 'MARKDOWN_VAULT_MCP_FTS_WEIGHTS=<MARKDOWN_VAULT_MCP_FTS_WEIGHTS>' -e 'MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=<MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER>' -e 'MARKDOWN_VAULT_MCP_OLLAMA_MODEL=nomic-embed-text' -e 'MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY=false' -e 'MARKDOWN_VAULT_MCP_VOYAGE_MODEL=voyage-4' -e 'MARKDOWN_VAULT_MCP_OPENAI_BASE_URL=https://api.openai.com/v1' -e 'MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL=text-embedding-3-small' -e 'MARKDOWN_VAULT_MCP_FASTEMBED_MODEL=BAAI/bge-small-en-v1.5' -e 'MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR=<MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR>' -e 'MARKDOWN_VAULT_MCP_EMBED_CONTEXT=false' -e 'MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S=30.0' -e 'MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE=4' -e 'MARKDOWN_VAULT_MCP_GIT_TOKEN=<your markdown_vault_mcp_git_token>' -e 'MARKDOWN_VAULT_MCP_GIT_REPO_URL=<MARKDOWN_VAULT_MCP_GIT_REPO_URL>' -e 'MARKDOWN_VAULT_MCP_GIT_USERNAME=x-access-token' -e 'MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S=600' -e 'MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S=30.0' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME=markdown-vault-mcp' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL=noreply@markdown-vault-mcp' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM=<MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM>' -e 'MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM=<MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM>' -e 'MARKDOWN_VAULT_MCP_GIT_LFS=true' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER=true' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S=2.0' -e 'MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR=true' -e 'MARKDOWN_VAULT_MCP_BOOT_REINDEX=true' -e 'MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET=<your markdown_vault_mcp_github_webhook_secret>' -e 'MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN=<your markdown_vault_mcp_gitlab_webhook_signing_token>' -e 'MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN=<your markdown_vault_mcp_gitlab_webhook_secret_token>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER=<MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY=<your markdown_vault_mcp_summarize_openai_api_key>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL=<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL>' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL=gpt-5-mini' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS=8192' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES=50' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS=200000' -e 'MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT=120.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S=3600.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S=86400.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S=60.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S=60.0' -e 'MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES=104857600' -e 'MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S=25.0' -e 'MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S=3600.0' -e 'MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT=256' -- docker run -i --rm ghcr.io/pvliesdonk/markdown-vault-mcp:v5.1.0 --port

{
    "mcpServers": {
        "markdown-vault-mcp": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "ghcr.io/pvliesdonk/markdown-vault-mcp:v5.1.0",
                "--port"
            ],
            "env": {
                "MARKDOWN_VAULT_MCP_SHUTDOWN_GRACE_S": "3",
                "MARKDOWN_VAULT_MCP_BASE_URL": "<MARKDOWN_VAULT_MCP_BASE_URL>",
                "MARKDOWN_VAULT_MCP_BEARER_TOKEN": "<your markdown_vault_mcp_bearer_token>",
                "MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL": "<MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL>",
                "MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID": "<MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID>",
                "MARKDOWN_VAULT_MCP_OIDC_CLIENT_SECRET": "<your markdown_vault_mcp_oidc_client_secret>",
                "MARKDOWN_VAULT_MCP_OIDC_AUDIENCE": "<MARKDOWN_VAULT_MCP_OIDC_AUDIENCE>",
                "MARKDOWN_VAULT_MCP_OIDC_REQUIRED_SCOPES": "openid",
                "MARKDOWN_VAULT_MCP_OIDC_ADVERTISED_SCOPES": "openid offline_access",
                "MARKDOWN_VAULT_MCP_OIDC_JWT_SIGNING_KEY": "<your markdown_vault_mcp_oidc_jwt_signing_key>",
                "MARKDOWN_VAULT_MCP_OIDC_VERIFY_ACCESS_TOKEN": "false",
                "MARKDOWN_VAULT_MCP_KV_STORE_URL": "file:///data/state",
                "MARKDOWN_VAULT_MCP_APP_DOMAIN": "<MARKDOWN_VAULT_MCP_APP_DOMAIN>",
                "MARKDOWN_VAULT_MCP_TOOLS_ALLOW": "<MARKDOWN_VAULT_MCP_TOOLS_ALLOW>",
                "MARKDOWN_VAULT_MCP_TOOLS_DENY": "<MARKDOWN_VAULT_MCP_TOOLS_DENY>",
                "MARKDOWN_VAULT_MCP_AUTH_MODE": "<MARKDOWN_VAULT_MCP_AUTH_MODE>",
                "MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE": "<MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE>",
                "MARKDOWN_VAULT_MCP_BEARER_DEFAULT_SUBJECT": "bearer-anon",
                "MARKDOWN_VAULT_MCP_SERVER_NAME": "<MARKDOWN_VAULT_MCP_SERVER_NAME>",
                "MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION": "<MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION>",
                "MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA": "<MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA>",
                "MARKDOWN_VAULT_MCP_INSTRUCTIONS": "<MARKDOWN_VAULT_MCP_INSTRUCTIONS>",
                "MARKDOWN_VAULT_MCP_HTTP_PATH": "/mcp",
                "MARKDOWN_VAULT_MCP_HEALTH_DETAIL": "standard",
                "PUID": "1000",
                "PGID": "1000",
                "MARKDOWN_VAULT_MCP_LOG_LEVEL": "INFO",
                "MARKDOWN_VAULT_MCP_LOG_FORMAT": "<MARKDOWN_VAULT_MCP_LOG_FORMAT>",
                "OLLAMA_HOST": "http://localhost:11434",
                "OPENAI_API_KEY": "<your openai_api_key>",
                "VOYAGE_API_KEY": "<your voyage_api_key>",
                "OPENAI_BASE_URL": "<OPENAI_BASE_URL>",
                "OPENAI_EMBEDDING_MODEL": "<OPENAI_EMBEDDING_MODEL>",
                "MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S": "60",
                "MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S": "60",
                "MARKDOWN_VAULT_MCP_SOURCE_DIR": "/data/vault",
                "MARKDOWN_VAULT_MCP_READ_ONLY": "false",
                "MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING": "true",
                "MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS": "false",
                "MARKDOWN_VAULT_MCP_DISABLE_APPS_UI": "false",
                "MARKDOWN_VAULT_MCP_INDEX_PATH": "<MARKDOWN_VAULT_MCP_INDEX_PATH>",
                "MARKDOWN_VAULT_MCP_STATE_PATH": "<MARKDOWN_VAULT_MCP_STATE_PATH>",
                "MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH": "<MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH>",
                "MARKDOWN_VAULT_MCP_INDEXED_FIELDS": "<MARKDOWN_VAULT_MCP_INDEXED_FIELDS>",
                "MARKDOWN_VAULT_MCP_REQUIRED_FIELDS": "<MARKDOWN_VAULT_MCP_REQUIRED_FIELDS>",
                "MARKDOWN_VAULT_MCP_EXCLUDE": "<MARKDOWN_VAULT_MCP_EXCLUDE>",
                "MARKDOWN_VAULT_MCP_TITLE_FIELD": "title",
                "MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS": "<MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS>",
                "MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER": "_templates",
                "MARKDOWN_VAULT_MCP_PROMPTS_FOLDER": "<MARKDOWN_VAULT_MCP_PROMPTS_FOLDER>",
                "MARKDOWN_VAULT_MCP_CONVENTIONS_FILE": "_conventions.md",
                "MARKDOWN_VAULT_MCP_OKF_MODE": "auto",
                "MARKDOWN_VAULT_MCP_OKF_WRITE": "false",
                "MARKDOWN_VAULT_MCP_OKF_VERIFY": "elicit",
                "MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS": "<MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS>",
                "MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB": "1.0",
                "MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES": "262144",
                "MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE": "auto",
                "MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE": "2",
                "MARKDOWN_VAULT_MCP_SNIPPET_WORDS": "200",
                "MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA": "0.25",
                "MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS": "400",
                "MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS": "<MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS>",
                "MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS": "40",
                "MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS": "<MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS>",
                "MARKDOWN_VAULT_MCP_FTS_WEIGHTS": "<MARKDOWN_VAULT_MCP_FTS_WEIGHTS>",
                "MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER": "<MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER>",
                "MARKDOWN_VAULT_MCP_OLLAMA_MODEL": "nomic-embed-text",
                "MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY": "false",
                "MARKDOWN_VAULT_MCP_VOYAGE_MODEL": "voyage-4",
                "MARKDOWN_VAULT_MCP_OPENAI_BASE_URL": "https://api.openai.com/v1",
                "MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL": "text-embedding-3-small",
                "MARKDOWN_VAULT_MCP_FASTEMBED_MODEL": "BAAI/bge-small-en-v1.5",
                "MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR": "<MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR>",
                "MARKDOWN_VAULT_MCP_EMBED_CONTEXT": "false",
                "MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S": "30.0",
                "MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE": "4",
                "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<your markdown_vault_mcp_git_token>",
                "MARKDOWN_VAULT_MCP_GIT_REPO_URL": "<MARKDOWN_VAULT_MCP_GIT_REPO_URL>",
                "MARKDOWN_VAULT_MCP_GIT_USERNAME": "x-access-token",
                "MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S": "600",
                "MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S": "30.0",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME": "markdown-vault-mcp",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL": "noreply@markdown-vault-mcp",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM": "<MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM>",
                "MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM": "<MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM>",
                "MARKDOWN_VAULT_MCP_GIT_LFS": "true",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER": "true",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S": "2.0",
                "MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR": "true",
                "MARKDOWN_VAULT_MCP_BOOT_REINDEX": "true",
                "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<your markdown_vault_mcp_github_webhook_secret>",
                "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<your markdown_vault_mcp_gitlab_webhook_signing_token>",
                "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<your markdown_vault_mcp_gitlab_webhook_secret_token>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER": "<MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<your markdown_vault_mcp_summarize_openai_api_key>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL>",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL": "gpt-5-mini",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS": "8192",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES": "50",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS": "200000",
                "MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT": "120.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S": "3600.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S": "86400.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S": "60.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S": "60.0",
                "MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES": "104857600",
                "MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S": "25.0",
                "MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S": "3600.0",
                "MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT": "256"
            }
        }
    }
}

Variables d'environnement

• MARKDOWN_VAULT_MCP_SHUTDOWN_GRACE_S Seconds SIGTERM may spend draining in-flight requests before the HTTP server exits. Keep it at or below the termination grace period the orchestrator allows. `0` drops in-flight requests immediately.
• MARKDOWN_VAULT_MCP_BASE_URL Public base URL of the deployed server, for example `https://mcp.example.com`. Required for OIDC. Also the fallback source of the MCP Apps domain when `app_domain` is unset.
• MARKDOWN_VAULT_MCP_BEARER_TOKEN secret Single shared bearer token; enables bearer auth unless `bearer_tokens_file` is set, which takes precedence.
• MARKDOWN_VAULT_MCP_OIDC_CONFIG_URL OIDC discovery document URL, for example `https://auth.example.com/.well-known/openid-configuration`.
• MARKDOWN_VAULT_MCP_OIDC_CLIENT_ID OIDC client identifier registered with the provider.
• MARKDOWN_VAULT_MCP_OIDC_CLIENT_SECRET secret OIDC client secret registered with the provider.
• MARKDOWN_VAULT_MCP_OIDC_AUDIENCE Expected `aud` claim; tokens issued for another audience are rejected.
• MARKDOWN_VAULT_MCP_OIDC_REQUIRED_SCOPES Scopes a caller must present, space- or comma-separated. Defaults to `openid` in oidc-proxy mode.
• MARKDOWN_VAULT_MCP_OIDC_ADVERTISED_SCOPES Scopes advertised to MCP clients in protected-resource metadata, space- or comma-separated. Overrides the default `openid offline_access`; `oidc_required_scopes` is always added on top. Set this when the registered client is not permitted `offline_access`, or to have clients request extra claim scopes (such as `groups`) without also requiring them in every token.
• MARKDOWN_VAULT_MCP_OIDC_JWT_SIGNING_KEY secret Signing key for issued tokens; used in oidc-proxy mode only. When unset, the key is derived deterministically from `oidc_client_secret`, so tokens survive a restart. Rotating that secret then invalidates every issued token. Set this explicitly to decouple token validity from secret rotation. Generate with `openssl rand -hex 32`.
• MARKDOWN_VAULT_MCP_OIDC_VERIFY_ACCESS_TOKEN Validate the access token instead of the id token.
• MARKDOWN_VAULT_MCP_KV_STORE_URL Persistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` (with a warning) on a host where that directory is not usable.
• MARKDOWN_VAULT_MCP_APP_DOMAIN MCP Apps iframe domain, used for CSP sandboxing. Overrides the host derived from `base_url`.
• MARKDOWN_VAULT_MCP_TOOLS_ALLOW Comma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`.
• MARKDOWN_VAULT_MCP_TOOLS_DENY Comma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`.
• MARKDOWN_VAULT_MCP_AUTH_MODE Explicit auth-mode override, accepting `remote` or `oidc-proxy` (case- and whitespace-insensitive). When unset the mode is auto-detected from which auth variables are set; the override exists because having all four OIDC variables set is ambiguous between those two modes. Other values are ignored with a warning.
• MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILE Path to a TOML file mapping bearer tokens to subjects; overrides the single-token `bearer_token` mode.
• MARKDOWN_VAULT_MCP_BEARER_DEFAULT_SUBJECT Subject assigned to the single-token bearer mode; ignored when `bearer_tokens_file` is set, since mapped mode carries per-token subjects.
• MARKDOWN_VAULT_MCP_SERVER_NAME Rename this server instance; defaults to the project name.
• MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTION Concise routing context that distinguishes this deployment's material or responsibility.
• MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRA Deployment-specific behavioral policy added to the generated MCP instructions.
• MARKDOWN_VAULT_MCP_INSTRUCTIONS Legacy: replaces all generated MCP instructions (deprecated; use _INSTANCE_DESCRIPTION for routing and _INSTRUCTIONS_EXTRA for policy).
• MARKDOWN_VAULT_MCP_HTTP_PATH Mount path for the MCP endpoint; the health routes derive their prefix from it.
• MARKDOWN_VAULT_MCP_HEALTH_DETAIL How much the unauthenticated /health and /health/ready bodies say: status, standard (adds name, version and per-check verdicts), or full (adds redacted reasons; trusted networks only).
• PUID Run the server process as this UID; the container entrypoint reassigns ownership of writable paths to match.
• PGID Run the server process as this GID; pair with PUID to match the owner of a mounted volume.
• MARKDOWN_VAULT_MCP_LOG_LEVEL Log level for every logger in the process, FastMCP's included (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. The unprefixed FASTMCP_LOG_LEVEL still works for one major version and logs a deprecation warning.
• MARKDOWN_VAULT_MCP_LOG_FORMAT Log rendering. rich is one colour event key=value line per record, for a terminal; json is one JSON object per record, for a collector. Unset picks rich when stderr is a terminal and json everywhere else, so a container or journald gets JSON with no configuration.
• OLLAMA_HOST Ollama server URL for the ollama embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the Ollama ecosystem convention.
• OPENAI_API_KEY secret OpenAI API key for the openai embedding provider, and the fallback key for the summarize tool when MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY is unset. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OpenAI ecosystem convention.
• VOYAGE_API_KEY secret Voyage AI API key for the voyage embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OPENAI_API_KEY / OLLAMA_HOST convention. Setting it never auto-selects the provider; choose it explicitly with MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=voyage.
• OPENAI_BASE_URL Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_BASE_URL (embeddings). For the summarize tool it only routes traffic when an API key already enables the feature; it never enables summarize by itself.
• OPENAI_EMBEDDING_MODEL Bare fallback for MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL.
• MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_S Maximum seconds an index-backed tool or resource waits for the FTS index to become queryable during a cold-start background build before raising IndexUnavailableError(reason="timeout"). Increase for large vaults.
• MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_S Maximum seconds an index-querying read tool waits for the IndexWriter to drain when called with wait_for_pending_writes=true. On timeout the tool answers from the current index and reports index_stale=true in the response _meta.
• MARKDOWN_VAULT_MCP_SOURCE_DIR Path to the markdown vault directory. When it does not exist, or the server cannot access it, the server starts but every tool fails with a message saying which until it is fixed (managed git mode clones into it). Symbolic links inside the vault are followed on Python 3.13+.
• MARKDOWN_VAULT_MCP_READ_ONLY Set to true to hide the write tools (write, edit, append, delete, rename, move_folder, fetch, git_sync, the okf_* tools, create_upload_link) and serve a search-only vault.
• MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTING Refuse a write that would overwrite an existing file when no if_match etag is supplied. Deliberate replacement still works: read the file first, then pass if_match. Unaffected: edit, append, delete, rename. Set to false to allow blind overwrites.
• MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKS Set to true to have write, edit and append list, under unresolved_links, the target of each link the call added that get_broken_links reports. Links the note already held are left out. Off by default, leaving those responses unchanged.
• MARKDOWN_VAULT_MCP_DISABLE_APPS_UI Hide the MCP Apps UI tools (browse_vault, show_context) from the tool listing for clients that do not render MCP Apps panels.
• MARKDOWN_VAULT_MCP_INDEX_PATH Path to the SQLite FTS5 index file; unset keeps the index in memory. Set it for persistence across restarts.
• MARKDOWN_VAULT_MCP_STATE_PATH Path to the change-tracking state file. Defaults to INDEX_PATH plus .state.json (index.db.state.json beside index.db); without INDEX_PATH the state is kept in memory. Never written into the vault by default.
• MARKDOWN_VAULT_MCP_EMBEDDINGS_PATH Base path for the embeddings files. Defaults beside INDEX_PATH (index-db-embeddings.npy and .json beside index.db); without INDEX_PATH the vectors are kept in memory and rebuilt at each start. Setting it also lets the provider be auto-detected.
• MARKDOWN_VAULT_MCP_INDEXED_FIELDS Comma-separated frontmatter fields promoted to the tag index for structured filtering. Changing it cold-rebuilds the index once on next startup; SEARCHABLE_FIELDS inherits this value when unset.
• MARKDOWN_VAULT_MCP_REQUIRED_FIELDS Comma-separated frontmatter fields required on every document; documents missing any are excluded from the index.
• MARKDOWN_VAULT_MCP_EXCLUDE Comma-separated glob patterns excluded from scanning, e.g. .obsidian/**,.trash/**.
• MARKDOWN_VAULT_MCP_TITLE_FIELD Frontmatter field used as the document title (falls back to title, the first H1, then the filename). Changing it cold-rebuilds the index once on next startup.
• MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDS Comma-separated frontmatter fields whose text values become keyword-searchable and enrich first-chunk embeddings. Inherits INDEXED_FIELDS when unset; the sentinel none means filterable but not searchable. Changing it cold-rebuilds the index and re-embeds once on next startup.
• MARKDOWN_VAULT_MCP_TEMPLATES_FOLDER Relative folder where note templates live (used by the create_from_template prompt).
• MARKDOWN_VAULT_MCP_PROMPTS_FOLDER Directory of .md prompt files that extend or override built-in prompts; a relative path is resolved against SOURCE_DIR.
• MARKDOWN_VAULT_MCP_CONVENTIONS_FILE Filename of the per-folder conventions files surfaced to clients at write time (bare .md filename without glob characters). Set to none to disable folder conventions.
• MARKDOWN_VAULT_MCP_OKF_MODE OKF (Open Knowledge Format) read semantics. With auto (the default), read annotations switch on when the vault declares an OKF version in its root index.md. Use off to disable OKF semantics entirely, or on to force them for an undeclared vault. Annotations are read-only; write behavior is never affected.
• MARKDOWN_VAULT_MCP_OKF_WRITE OKF (Open Knowledge Format) enforced write layer. When true on an OKF-active vault, the server stamps generated provenance on each write and clears any verified attestation when a note's content changes. It also keeps each written folder's log.md and index.md current, and exposes the okf_verify tool. Requires OKF_MODE to be auto or on (a true value with OKF_MODE=off is a config error). Off by default.
• MARKDOWN_VAULT_MCP_OKF_VERIFY How the okf_verify tool attributes a human review. This applies only when OKF_WRITE is on, which gates the tool. With elicit (the default), okf_verify asks the human to confirm the review through an MCP elicitation, then records the attestation only on an affirmative reply. It fails closed when the client cannot elicit or the human declines, so a model holding the human's token cannot self-attest. Set trust-auth instead to attribute to a token's sub claim with no confirmation; it rejects static bearer credentials and other client-ID-only identities. This is safe only when the sole caller is a human-driven UI. Set off to hide the tool, leaving attestation to external tooling. A non-default value with OKF_WRITE off is a config error.
• MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONS Comma-separated allowed attachment extensions (e.g. pdf,png,jpg); case and a leading dot are ignored, so PDF and .pdf name the same type. Use * to allow every non-markdown file. Unset selects the built-in allowlist. A link whose target has a listed extension is not part of the link graph; changing the list rebuilds the index once.
• MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MB Maximum attachment size in MB returned by read / accepted by write; 0 disables the limit.
• MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTES Maximum bytes returned by a full-document read of a note; use `read(path, section=…)` for partial reads. 0 disables the limit.
• MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODE Mode used when a search call omits 'mode': auto, keyword, semantic, or hybrid. The default 'auto' picks hybrid when embeddings are configured and keyword when they are not. Pin 'keyword' to keep unqualified searches off the embedding provider (each hybrid or semantic search embeds the query, which costs an API call on a metered provider). A configured semantic/hybrid default also degrades to keyword without embeddings, so no setting can make a vault unsearchable; an explicit mode= argument is never downgraded.
• MARKDOWN_VAULT_MCP_CHUNKS_PER_FILE Maximum chunks returned per document in search results.
• MARKDOWN_VAULT_MCP_SNIPPET_WORDS Width of the snippet window (words) in search results; 0 returns full chunk content.
• MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHA Down-weights longer chunks in ranking: score / (1 + alpha * log(chunk_count)).
• MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDS Word cap per chunk; the adaptive chunker splits at deeper heading levels, then paragraph/word boundaries, to respect it. Match it to the embedding model's context. A reindex applies a new value.
• MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARS Character cap enforced alongside MAX_CHUNK_WORDS to bound token-dense chunks. Unset derives min(1500, model context * 2.8). Set a positive value for an exact cap, or -1 to scale with the model's full context (can exhaust memory on long-context models). A reindex applies a new value.
• MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDS Words of overlap between adjacent budget-split fragments of the same heading section (0 disables). A reindex applies a new value.
• MARKDOWN_VAULT_MCP_FOLDER_WEIGHTS Folder-prefix score multipliers (`prefix:weight` pairs, comma-separated, weights > 0) applied to all search modes; the deepest matching prefix wins (sessions:0.5 demotes sessions/**).
• MARKDOWN_VAULT_MCP_FTS_WEIGHTS Per-column BM25 weights (`column:weight` pairs, comma-separated, weights >= 0) for keyword ranking. Columns: path, title, folder, heading, content, summary.
• MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER Embedding provider: openai, voyage, ollama, or fastembed; setting it turns on search by meaning. Unset auto-detects from the environment (never voyage), but only when EMBEDDINGS_PATH is set. Any OpenAI-compatible endpoint works with openai plus OPENAI_BASE_URL; see the embeddings guide.
• MARKDOWN_VAULT_MCP_OLLAMA_MODEL Ollama embedding model name.
• MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLY Force Ollama to embed on CPU only.
• MARKDOWN_VAULT_MCP_VOYAGE_MODEL Voyage AI embedding model name.
• MARKDOWN_VAULT_MCP_OPENAI_BASE_URL OpenAI-compatible API base URL for embeddings; the bare OPENAI_BASE_URL is honoured as a fallback.
• MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL OpenAI-compatible embedding model name; the bare OPENAI_EMBEDDING_MODEL is honoured as a fallback.
• MARKDOWN_VAULT_MCP_FASTEMBED_MODEL FastEmbed model name.
• MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIR FastEmbed model cache directory (in Docker, stored under /data/state/fastembed).
• MARKDOWN_VAULT_MCP_EMBED_CONTEXT Enrich embedding input with the note title, chunk heading, and (first chunk) searchable-field values. Flipping it re-embeds the whole vault once on next startup.
• MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_S Per-request wall-clock budget in seconds for a single embedding HTTP call (OpenAI/Ollama). The local FastEmbed backend runs in-process with no network call and ignores this. CPU-only or large-model workloads may need 60-120 s; raise this if batches time out.
• MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZE Number of chunks sent per embedding request. Smaller batches shorten each request (useful under a tight timeout on slow models) at the cost of more round-trips.
• MARKDOWN_VAULT_MCP_GIT_TOKEN secret Token/password for HTTPS git auth; remotes must be HTTPS when set.
• MARKDOWN_VAULT_MCP_GIT_REPO_URL HTTPS remote URL for managed git mode: the server clones into an empty SOURCE_DIR on startup (or validates an existing origin) and enables the pull loop, auto-commit, and deferred push.
• MARKDOWN_VAULT_MCP_GIT_USERNAME Username for HTTPS git auth prompts (x-access-token for GitHub, oauth2 for GitLab, the account name for Bitbucket).
• MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_S Seconds between git fetch + fast-forward update attempts; 0 disables periodic pull.
• MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_S Seconds of write-idle time before pushing; 0 pushes only on shutdown.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME Git committer name for auto-commits, and the author name too unless an OIDC claim supplies one; set this in Docker where git config user.name is empty.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL Git committer email for auto-commits, and the author email too unless an OIDC claim supplies one.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIM OIDC claim key used as the commit author name (e.g. name) when an OIDC token is present; the committer stays GIT_COMMIT_NAME. The claim is resolved when the tool call arrives and carried to the background commit, so it applies on every write. A configured claim the token does not carry is reported once at WARNING and the static identity is used.
• MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIM OIDC claim key used as the commit author email (e.g. email) when an OIDC token is present; the committer stays GIT_COMMIT_EMAIL. Resolved and carried the same way as the name claim.
• MARKDOWN_VAULT_MCP_GIT_LFS Run git lfs pull on startup to fetch LFS-tracked attachments; set to false for repos without LFS.
• MARKDOWN_VAULT_MCP_FILE_WATCHER Watch the vault for external filesystem changes; auto-disabled when git pull is active or a webhook can deliver (HTTP/SSE transports only). Requires the file-watcher extra.
• MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_S Seconds of quiet after the last filesystem event before reindexing.
• MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOOR Keep the non-recursive watch on the vault root; set false to register zero source-dir-rooted FSEvents streams (avoids repeated macOS access prompts on a home-rooted vault) at the cost of root-level files relying on scans.
• MARKDOWN_VAULT_MCP_BOOT_REINDEX Reconcile offline changes at startup by reindexing once the initial build completes. Set false on a large vault to start without paying a full filesystem scan per server start; changes made while no server was running are then invisible until a reindex runs (the reindex tool, or 'markdown-vault-mcp reindex'). Note that `index_stale` reports writer idleness, not agreement with disk, so it reads false while the index may still differ from the vault.
• MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET secret Shared secret for the GitHub push-event webhook; when set, mounts POST /github-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events.
• MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN secret Signing token for the GitLab push-event webhook (GitLab 19.0+); when set, mounts POST /gitlab-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. GitLab generates this value; copy the `whsec_` token it shows under Generate signing token rather than inventing one. Deliveries are authenticated by HMAC-SHA256 over the webhook id, timestamp and body, and a delivery older than 5 minutes is rejected.
• MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN secret Secret token for the GitLab push-event webhook, GitLab's plain-text form and the only one below 19.0; also mounts POST /gitlab-webhook. It proves nothing about the body and cannot expire, so prefer the signing token where the GitLab version offers it. Setting both accepts either, which is how an existing webhook migrates.
• MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDER Summarization backend (only openai is recognised). Unset auto-detects: the backend activates when credentials or an explicit endpoint are present.
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY secret API key for the OpenAI-compatible summarize endpoint; the bare OPENAI_API_KEY is honoured as a fallback. Unset works for keyless local endpoints (Ollama).
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URL OpenAI-compatible endpoint base URL for the summarize tool; setting it enables the tool even without an API key. The bare OPENAI_BASE_URL routes traffic only when a key already enables the feature.
• MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODEL Chat model id used for summaries.
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENS Upper bound on generated tokens per summarize call; on reasoning models this budget also covers internal reasoning tokens.
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTES Cap on the number of notes summarised in one call (subtree expansion truncates to this many).
• MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARS Aggregate cap on note characters sent to the model in one call; excess is truncated with a flag on the result.
• MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUT Per-request wall-clock budget in seconds for a single summarize backend call; keep it below the MCP client's request timeout so the server-side error wins the race.
• MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_S Link lifetime in seconds when the caller requests no explicit TTL.
• MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_S Ceiling in seconds a caller-requested link TTL is clamped to.
• MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_S Post-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.
• MARKDOWN_VAULT_MCP_TRANSFER_LEASE_S Crashed-handler reclaim window in seconds for an in-flight reservation.
• MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTES Maximum size in bytes of a single upload.
• MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_S Seconds a long-running tool call may run in the foreground before it is promoted to a background job and a job handle is returned instead.
• MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_S Seconds a background-job record (working or finished) is retained for polling before it expires from the store.
• MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECT Maximum live background jobs per calling subject; further promotions are rejected until older records expire.