io.github.Studio-Moser/shelbymcp

Official registry AI and agents

Knowledge-graph memory server for AI tools via MCP

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package shelbymcp
Claude Code
claude mcp add shelbymcp -- npx -y shelbymcp@0.2.4
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "shelbymcp": {
            "command": "npx",
            "args": [
                "-y",
                "shelbymcp@0.2.4"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Quick start
  2. What agents can do
  3. HTTP and OAuth
  4. Build from source
  5. Reuse in Shelby App
  6. License

Local knowledge-graph memory for AI tools, implemented as one Rust binary.

ShelbyMCP gives MCP-compatible agents durable memory across sessions. Thoughts live in a local SQLite database with FTS5 search, optional vectors, typed graph edges, project scope, trust fencing, and curated context briefs. The server performs no inference and makes no model API calls.

Quick start

Run the platform-native binary through npm:

npx -y shelbymcp --version
npx -y shelbymcp

The default stdio server stores data at ~/.shelbymcp/memory.db. Existing databases created by ShelbyMCP schema v18 open unchanged.

Package-first integrations are included in the protected v0.4.0 release:

ClientRelease package
ChatGPT / Codexshelbymcp-codex-0.4.0.zip
Claude Codeshelbymcp-claude-code-0.4.0.zip
Cursor and Agent Plugins clientsshelbymcp-agent-plugin-0.4.0.zip
Gemini CLIshelbymcp-gemini-0.4.0.zip
Antigravityshelbymcp-antigravity-0.4.0.zip
Claude Desktopshelbymcp-claude-desktop-<platform>-0.4.0.mcpb
Devinshelbymcp-devin-0.4.0.zip

Use shelby-mcp setup <client> only when the client package or marketplace entry is not available yet. The fallback supports claude-code, claude-desktop, cursor, codex, gemini, and antigravity; devin directs you to its organization-managed marketplace, while windsurf keeps the legacy local config flow. It safely merges the MCP entry and never appends instructions to a global rules file. See Agent Setup.

What agents can do

The server exposes 12 MCP tools:

  • Capture, search, list, fetch, update, and delete thoughts.
  • Link and traverse typed graph edges with manage_edges, explore_graph, and expand_neighbors.
  • Build trusted, token-bounded context with get_brief and select_context.
  • Audit the database with thought_stats.

Search returns summaries and IDs so clients can fetch full content only when needed. Project-aware operations resolve scope from MCP roots and fail closed when the project cannot be identified. Untrusted or external memories are returned inside explicit data-only fences.

The optional Forage and Onboard skills are packaged with supported clients. They run in the user's agent session; ShelbyMCP does not receive or store model credentials. Standalone prompt bodies remain available:

shelby-mcp forage
shelby-mcp onboard
shelby-mcp migrate
shelby-mcp protocol

HTTP and OAuth

Start Streamable HTTP on port 3100:

SHELBY_API_KEY="replace-with-a-long-random-secret" \
  npx -y shelbymcp --transport http --host 127.0.0.1 --port 3100

Endpoints include /mcp, /health, and MCP discovery documents. Setting SHELBY_API_KEY enables bearer authentication and an OAuth authorization-code flow with protected-resource discovery, S256 PKCE, dynamic client registration, and resource-bound access and refresh tokens. Tokens do not expire or rotate; rotate SHELBY_API_KEY to revoke them. Without it, HTTP runs unauthenticated and the OAuth endpoints return 503; do not bind an unauthenticated server to an untrusted network.

Build from source

git clone https://github.com/Studio-Moser/shelbymcp.git
cd shelbymcp
cargo build -p shelby-mcp
cargo test --workspace
npm ci
npm test

Rust owns the product. Node is used only for the small npm launcher, packaging scripts, and their tests. See Development and Architecture.

Memory-engine pull requests also run a deterministic contract and public retrieval gate. See [Memory evaluation](<docs/Memory Evaluation.md>).

Reuse in Shelby App

The workspace is intentionally layered for the cross-platform Shelby App:

  • shelby-memory is the SQLite memory engine and all memory-domain behavior.
  • shelby-integrations is the current client catalog plus safe setup/status/uninstall helpers.
  • shelby-mcp exposes the MCP service and reusable Axum router as a library as well as a binary.

The app can embed these crates in-process, share one database contract across macOS and iOS, and host the same HTTP router without spawning Node.

License

MIT. See LICENSE.

Frequently asked questions

What is io.github.Studio-Moser/shelbymcp?

Knowledge-graph memory server for AI tools via MCP

How do I install io.github.Studio-Moser/shelbymcp?

It runs on your machine. In Claude Code: claude mcp add shelbymcp -- npx -y shelbymcp@0.2.4. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.Studio-Moser/shelbymcp need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.Studio-Moser/shelbymcp open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains io.github.Studio-Moser/shelbymcp?

It is published by Studio-Moser. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.