Langfuse Prompt Management MCP Server

What is Langfuse Prompt Management MCP Server about?

Provides an MCP‑compatible endpoint that surfaces Langfuse‑hosted prompts, enabling clients (e.g., Claude Desktop, Cursor) to list, retrieve, and compile prompts without writing custom Langfuse API code.

How to use Langfuse Prompt Management MCP Server?

1. Build the server

   npm install
   npm run build
   

2. Configure an MCP client (Claude Desktop example): add an entry to claude_desktop_config.json pointing to the built index.js and set the required environment variables (LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, LANGFUSE_BASEURL).
3. Run the server

   node /absolute/path/to/build/index.js
   

4. Invoke MCP methods such as prompts/list or prompts/get (or the equivalent tool calls get-prompts / get-prompt) from the client.

Key features of Langfuse Prompt Management MCP Server

• MCP Prompt specification implementation (prompts/list, prompts/get).
• Cursor‑based pagination for listing large prompt collections.
• Automatic conversion of Langfuse text and chat prompts into MCP prompt objects.
• Variable compilation: inject supplied arguments into the prompt template.
• Tool fallback (get-prompts, get-prompt) for clients that do not support the native prompt capability.
• Simple deployment via standard Node.js/npm workflow.

Use cases of Langfuse Prompt Management MCP Server

• Centralized prompt library for multiple AI agents across an organization.
• Seamless integration of Langfuse prompts into Claude Desktop, Cursor, or any MCP‑compatible IDE.
• Rapid prototyping of LLM applications where prompts are managed in Langfuse but consumed through MCP.
• Enabling non‑technical users to browse and select prompts via familiar UI tools.

FAQ

Q: Which prompts are exposed? A: Only prompts labeled production in Langfuse are returned.

Q: Are prompt arguments optional? A: Yes. All arguments are treated as optional because Langfuse does not supply argument metadata.

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

Q: Does the server fetch prompts efficiently? A: Listing requires fetching each prompt individually to extract arguments, which works but is not highly efficient.

Q: Can I contribute improvements? A: Absolutely—open an issue or PR 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.