Litefuse Docs MCP Server

The Litefuse Docs MCP server exposes the Litefuse docs to AI agents.

Core use case: Use Cursor (or other AI Coding Agent) to automatically integrate Litefuse Tracing into your codebase, see get started for detailed instructions and an example prompt.

This is the public MCP server for the Litefuse documentation. There is also an authenticated MCP server to integrate with the rest of the Litefuse data platform (docs).

Install

Add Langfuse Docs MCP to Cursor via the one-click install:

Install MCP Server in Cursor

Manual configuration

Add the following to your mcp.json:

{
  "mcpServers": {
    "langfuse-docs": {
      "url": "https://litefuse.ai/api/mcp"
    }
  }
}

Add Langfuse Docs MCP to Copilot in VSCode via the one-click install:

Install MCP Server in VS Code

Manual configuration

Add Langfuse Docs MCP to Copilot in VSCode via the following steps:

Open Command Palette (⌘+Shift+P)
Open “MCP: Add Server…”
Select HTTP
Paste https://litefuse.ai/api/mcp
Select name (e.g. langfuse-docs) and whether to save in user or workspace settings
You’re all set! The MCP server is now available in Agent mode

Add Langfuse Docs MCP to Claude Code via the CLI:

claude mcp add \
  --transport http \
  langfuse-docs \
  https://litefuse.ai/api/mcp \
  --scope user

Manual configuration

Alternatively, add the following to your settings file:

User scope: ~/.claude/settings.json
Project scope: your-repo/.claude/settings.json
Local scope: your-repo/.claude/settings.local.json

{
  "mcpServers": {
    "langfuse-docs": {
      "transportType": "http",
      "url": "https://litefuse.ai/api/mcp",
      "verifySsl": true
    }
  }
}

One-liner JSON import

claude mcp add-json langfuse-docs \
  '{"type":"http","url":"https://litefuse.ai/api/mcp"}'

Once added, start a Claude Code session (claude) and type /mcp to confirm the connection.

Add Langfuse Docs MCP to Windsurf via the following steps:

Open Command Palette (⌘+Shift+P)
Open “MCP Configuration Panel”
Select Add custom server

Add the following configuration:

{
  "mcpServers": {
    "langfuse-docs": {
      "command": "npx",
      "args": ["mcp-remote", "https://litefuse.ai/api/mcp"]
    }
  }
}

Langfuse uses the streamableHttp protocol to communicate with the MCP server. This is supported by most clients.

{
  "mcpServers": {
    "langfuse-docs": {
      "url": "https://litefuse.ai/api/mcp"
    }
  }
}

If you use a client that does not support streamableHttp (e.g. Windsurf), you can use the mcp-remote command as a local proxy.

{
  "mcpServers": {
    "langfuse-docs": {
      "command": "npx",
      "args": ["mcp-remote", "https://litefuse.ai/api/mcp"]
    }
  }
}

About

Endpoint: https://litefuse.ai/api/mcp
Transport: streamableHttp
Authentication: None
Tools:
- searchLitefuseDocs: Semantic search (RAG) over the Litefuse documentation. Returns a concise answer synthesized from relevant docs. Use for broader questions; prefer getLitefuseDocsPage for specific pages. Powered by Inkeep RAG API.
- getLitefuseDocsPage: Fetch the raw Markdown for a specific Litefuse docs page. Accepts a docs path (e.g., /docs/observability/overview) or a full https://litefuse.ai URL. Use for specific pages, integrations, or code samples.
- getLitefuseOverview: Get a high-level index by fetching llms.txt. Use at the start of a session to discover key docs endpoints. Avoid repeated calls.

References

Implementation of the MCP server: mcp.ts
Agentic Onboarding powered by the MCP server
Ask AI: RAG chat with the Litefuse docs to get answers to your questions
litefuse.ai/llms.txt: concise overview with page titles and links to detailed sub-files (llms-docs.txt, llms-integrations.txt, llms-self-hosting.txt)

REST Endpoint

The underlying docs search (searchLitefuseDocs tool) is also available independently as a REST API at https://litefuse.ai/api/search-docs.

curl "https://litefuse.ai/api/search-docs?query=Litefuse+Docs+MCP+Server"

Use this endpoint directly when you need lightweight semantic search outside of MCP.

Glossary Security & Guardrails

Was this page helpful?

Support