Langfuse Prompt Management MCP Server

What is Langfuse Prompt Management MCP Server about?

Provides an MCP‑compatible server that exposes Langfuse prompts as MCP Prompt resources and as legacy tools, allowing LLM clients (e.g., Claude Desktop, Cursor) to list, retrieve, and compile prompts directly from Langfuse.

How to use Langfuse Prompt Management MCP Server?

1. Install dependencies

   npm install
   

2. Build the server

   npm run build
   

3. Configure MCP server (example for Claude Desktop or Cursor) by setting the required environment variables:
   • LANGFUSE_PUBLIC_KEY
   • LANGFUSE_SECRET_KEY
   • LANGFUSE_BASEURL
4. Run the server via the command defined in serverConfig (e.g., npx -y mcp-server-langfuse).
5. Add the server entry to your MCP client configuration so the client can call the provided endpoints.

Key features of Langfuse Prompt Management MCP Server

• MCP Prompt implementation
  • prompts/list with optional cursor pagination, returning prompt names and inferred optional arguments.
  • prompts/get that converts Langfuse text/chat prompts into MCP prompt objects and compiles them with supplied variables.
• Tool compatibility layer
  • get-prompts tool mirrors prompts/list for clients lacking native prompt support.
  • get-prompt tool mirrors prompts/get for direct retrieval and compilation.
• Environment‑driven configuration for secure API key handling.
• Open‑source and extensible – contributions welcome via GitHub.

Use cases of Langfuse Prompt Management MCP Server

• Centralized prompt library for teams using Langfuse, exposed to any MCP‑compatible LLM client.
• Dynamic prompt compilation in chat assistants that need to inject variables at runtime.
• Cross‑tool integration where tools like Claude Desktop or Cursor can retrieve prompts without custom code.
• Rapid prototyping of prompt‑driven workflows by listing available prompts directly in the IDE or AI assistant UI.

FAQ from the Langfuse Prompt Management MCP Server

Q: Which prompts are returned? A: Only prompts tagged with the production label in Langfuse are exposed.

Q: Are prompt arguments required? A: All arguments are treated as optional; descriptions are unavailable because Langfuse does not store variable metadata.

Q: How does pagination work? A: prompts/list supports a cursor parameter; the response includes a nextCursor when more pages exist.

Q: Can I use this with other MCP clients? A: Yes. The server also provides legacy tools (get‑prompts and get‑prompt) for clients that do not support the Prompt capability.

Q: What are the performance considerations? A: Listing prompts fetches each prompt individually to infer arguments, which may be slower for large libraries.

Q: How do I contribute? A: Open an issue or submit a pull request on the GitHub repository.

Langfuse Prompt Management MCP Server

Model Context Protocol (MCP) Server for Langfuse Prompt Management. This server allows you to access and manage your Langfuse prompts through the Model Context Protocol.

Demo

Quick demo of Langfuse Prompts MCP in Claude Desktop (unmute for voice-over explanations):

https://github.com/user-attachments/assets/61da79af-07c2-4f69-b28c-ca7c6e606405

Features

MCP Prompt

This server implements the MCP Prompts specification for prompt discovery and retrieval.

• prompts/list: List all available prompts

  • Optional cursor-based pagination
  • Returns prompt names and their required arguments, limitation: all arguments are assumed to be optional and do not include descriptions as variables do not have specification in Langfuse
  • Includes next cursor for pagination if there's more than 1 page of prompts

• prompts/get: Get a specific prompt

  • Transforms Langfuse prompts (text and chat) into MCP prompt objects
  • Compiles prompt with provided variables

Tools

To increase compatibility with other MCP clients that do not support the prompt capability, the server also exports tools that replicate the functionality of the MCP Prompts.

• get-prompts: List available prompts

  • Optional cursor parameter for pagination
  • Returns a list of prompts with their arguments

• get-prompt: Retrieve and compile a specific prompt

  • Required name parameter: Name of the prompt to retrieve
  • Optional arguments parameter: JSON object with prompt variables

Development

npm install

# build current file
npm run build

# test in mcp inspector
npx @modelcontextprotocol/inspector node ./build/index.js

Usage

Step 1: Build

npm install
npm run build

Step 2: Add the server to your MCP servers:

Claude Desktop

Configure Claude for Desktop by editing claude_desktop_config.json

{
  "mcpServers": {
    "langfuse": {
      "command": "node",
      "args": ["<absolute-path>/build/index.js"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "your-public-key",
        "LANGFUSE_SECRET_KEY": "your-secret-key",
        "LANGFUSE_BASEURL": "https://cloud.langfuse.com"
      }
    }
  }
}

Make sure to replace the environment variables with your actual Langfuse API keys. The server will now be available to use in Claude Desktop.

Cursor

Add new server to Cursor:

• Name: Langfuse Prompts
• Type: command
• Command:

  LANGFUSE_PUBLIC_KEY="your-public-key" LANGFUSE_SECRET_KEY="your-secret-key" LANGFUSE_BASEURL="https://cloud.langfuse.com" node absolute-path/build/index.js
  

Limitations

The MCP Server is a work in progress and has some limitations:

• Only prompts with a production label in Langfuse are returned
• All arguments are assumed to be optional and do not include descriptions as variables do not have specification in Langfuse
• List operations require fetching each prompt individually in the background to extract the arguments, this works but is not efficient

Contributions are welcome! Please open an issue or a PR (repo) if you have any suggestions or feedback.