Langfuse MCP

Communauté Données et bases de données

Read access to the Langfuse Public API: traces, observations, sessions, scores, prompts, datasets, metrics, models, projects and comments.

Installation

Les étapes d'installation sont dans la documentation ci-dessous. Documentation

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. langfuse-mcp
  2. Requirements
  3. Tools
  4. Install
  5. Configuration
  6. Use with Claude Desktop
  7. Use with Claude Code
  8. Use with Cursor
  9. Use with Cline (VS Code)
  10. Use with Continue
  11. Use with Windsurf
  12. Use with any other MCP client
  13. Try it
  14. Troubleshooting
  15. Development
  16. Contributing
  17. Security
  18. License

langfuse-mcp

An MCP server that exposes the Langfuse REST API as tools, so Claude (or any MCP client) can query your traces, observations, sessions, scores, prompts, datasets, and metrics during a conversation.

Useful when you want to ask things like:

  • "Why did trace abc123 fail? Walk me through its observations."
  • "List the 5 most recent traces with level=ERROR for user alice@x.com."
  • "Summarize today's generation cost broken down by model."
  • "Show me the production version of prompt customer-support-v2."

…without leaving your assistant.

Requirements

Tools

All tools are read-only and call the Langfuse Public API over HTTPS using your project keys for Basic Auth.

Traces & observations
ToolDescription
listTracesList traces with filters. Returns summary metadata.
getTraceFetch a single trace by id including the full observation tree.
listObservationsList spans, generations, and events with filters.
getObservationFetch a single observation by id.
Sessions
ToolDescription
listSessionsList sessions within a time range.
getSessionFetch a session by id, including its traces.
Scores
ToolDescription
listScoresList scores with filters.
getScoreFetch a single score by id.
listScoreConfigsList score configurations (definitions, ranges, categories).
getScoreConfigFetch a score configuration by id.
Prompts
ToolDescription
listPromptsList prompt definitions, optionally filtered by name, label, or tag.
getPromptFetch a prompt by name, optionally pinned to a specific version or label.
Datasets
ToolDescription
listDatasetsList datasets configured in Langfuse.
getDatasetFetch a dataset by name.
listDatasetItemsList items in a dataset (inputs, expected outputs, metadata).
getDatasetItemFetch a single dataset item by id.
listDatasetRunsList evaluation runs for a dataset.
getDatasetRunFetch a specific dataset run by name.
Metrics, models & misc
ToolDescription
getMetricsRun a custom metrics query (counts, latency, cost, token usage). Pass a JSON query string.
getDailyMetricsDaily aggregated usage / cost / count metrics.
listModelsList models known to Langfuse (for cost / token attribution).
getModelFetch a model definition by id.
listProjectsList projects accessible to the current API key.
listCommentsList comments attached to traces, observations, sessions, or prompts.
getCommentFetch a single comment by id.
getMediaFetch metadata for a media attachment (image, audio, file).
getHealthPing the Langfuse public health endpoint — useful for credential validation.

Install

Zero install with npx:

npx -y langfuse-mcp

Or install globally:

npm i -g langfuse-mcp
langfuse-mcp --version

Configuration

The server reads three environment variables:

VariableRequiredDescription
LANGFUSE_PUBLIC_KEYyesProject public key (pk-lf-…).
LANGFUSE_SECRET_KEYyesProject secret key (sk-lf-…).
LANGFUSE_BASE_URLyese.g. https://cloud.langfuse.com (EU) or https://us.cloud.langfuse.com (US) or your self-hosted URL.
LANGFUSE_ENV_FILEnoOptional path to a .env file to load instead of ./.env.

Where do I get my keys? In the Langfuse UI: Settings → API Keys → Create new API keys. Keys are scoped to a single project and a single region (EU vs US are separate accounts — match your LANGFUSE_BASE_URL to the region you created the keys in).

If a .env file exists in the working directory it will be loaded automatically. See .env.example for a starter file.

Use with Claude Desktop

Edit claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  }
}

Restart Claude Desktop after editing. The MCP server icon should appear in the chat input.

Use with Claude Code

Project-level (./.mcp.json):

{
  "mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  }
}

User-level config lives at ~/.claude.json and uses the same shape.

Use with Cursor

Project-level: .cursor/mcp.json. User-level: ~/.cursor/mcp.json.

{
  "mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  }
}

Use with Cline (VS Code)

In VS Code settings (settings.json):

{
  "cline.mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  }
}

Use with Continue

In ~/.continue/config.json:

{
  "mcpServers": [
    {
      "name": "langfuse",
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  ]
}

Use with Windsurf

In Windsurf's MCP settings, add:

{
  "mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": ["-y", "langfuse-mcp"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-…",
        "LANGFUSE_SECRET_KEY": "sk-lf-…",
        "LANGFUSE_BASE_URL": "https://cloud.langfuse.com"
      }
    }
  }
}

Use with any other MCP client

The server speaks MCP over stdio. Any MCP client can launch it as a subprocess:

LANGFUSE_PUBLIC_KEY=pk-lf-… \
LANGFUSE_SECRET_KEY=sk-lf-… \
LANGFUSE_BASE_URL=https://cloud.langfuse.com \
npx -y langfuse-mcp

Try it

Once wired up, ask your assistant things like:

  • "Use the getHealth tool to confirm langfuse-mcp is connected."
  • "List the 5 most recent traces with level=ERROR."
  • "Show me trace abc123 with all its observations."
  • "What scores did user alice@example.com receive this week?"
  • "Get the production version of prompt customer-support."
  • "List dataset runs for eval-2026-q1 and tell me which one had the highest accuracy score."

Troubleshooting

401 Unauthorized on the first call

  • Wrong region: Langfuse Cloud EU and US are separate accounts. Make sure LANGFUSE_BASE_URL matches the region where you created the keys (https://cloud.langfuse.com for EU, https://us.cloud.langfuse.com for US).
  • Quoted keys in .env: this server strips surrounding quotes, but a stray space can still break Basic Auth. Re-paste the key.
  • Use getHealth first to confirm credentials before running other tools.

npx keeps using an old version

npx -y langfuse-mcp@latest

npx caches packages aggressively. The @latest suffix forces a refresh.

LANGFUSE_BASE_URL must be a full URL error

The most common cause is a missing scheme. Use https://cloud.langfuse.com, not cloud.langfuse.com.

Self-hosted Langfuse

Use the full base URL of your deployment without a trailing slash or path. Example: https://langfuse.mycompany.internal. The server normalizes a single trailing slash, but anything else (/api, /public) will break path joining.

MCP server icon doesn't appear in Claude Desktop

  • Check the Claude Desktop log: ~/Library/Logs/Claude/mcp*.log (macOS) or %APPDATA%\Claude\Logs\ (Windows). The server writes a langfuse-mcp v… connected line to stderr on success.
  • Make sure Node 20+ is on your PATH (Claude Desktop uses your login shell PATH).
  • Quit Claude Desktop fully (not just close the window) and relaunch.

Cryptic ERR_REQUIRE_ESM / Unexpected token on startup

Your Node version is too old. This package requires Node ≥ 20. Run node --version and upgrade if needed (e.g. via nvm).

Development

git clone https://github.com/hugoles/langfuse-mcp.git
cd langfuse-mcp
npm install
cp .env.example .env       # macOS/Linux
copy .env.example .env     # Windows cmd
npm run dev                # tsx src/index.ts (no build step)

Other scripts:

ScriptWhat it does
npm run buildCompile TypeScript to dist/.
npm startRun the built server.
npm run typechecktsc --noEmit.
npm run lintESLint.
npm run format / npm run format:checkPrettier write / check.
npm testVitest.

Contributing

See CONTRIBUTING.md. Bug reports and PRs are welcome — please run npm run typecheck && npm run lint && npm test locally before opening one.

Security

Found a vulnerability? Please report it privately as described in SECURITY.md. Do not open a public issue.

License

MIT © Hugoles.

Questions fréquentes

Qu'est-ce que Langfuse MCP ?

Read access to the Langfuse Public API: traces, observations, sessions, scores, prompts, datasets, metrics, models, projects and comments.

Comment installer Langfuse MCP ?

Suivez les étapes d'installation de sa documentation, affichée sur cette page et dans son dépôt.

Langfuse MCP est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient Langfuse MCP ?

Il est publié par hugoles. AI.tn le référence sans le maintenir ni le recommander.

Issu des listes communautaires awesome-mcp-servers et du dépôt GitHub du projet. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.