Langfuse Prompt Management MCP Server

Source

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.

Catalog onlyCatalog onlySTDIO

Overview

Langfuse Prompt Management MCP Server is a server that allows users to access and manage Langfuse prompts through the Model Context Protocol (MCP). It facilitates prompt discovery and retrieval for various applications.

To use the server, you need to build it using npm, configure it with your Langfuse API keys, and add it to your MCP clients like Claude Desktop or Cursor.

Implements MCP Prompts specification for prompt discovery and retrieval. - Provides endpoints to list available prompts and retrieve specific prompts. - Exports tools for compatibility with other MCP clients.

Managing and retrieving prompts for AI applications.
Integrating with various MCP clients for enhanced functionality.
Facilitating prompt management in development environments.

Add to your AI client

Use these steps to connect Langfuse Prompt Management MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server-langfuse-langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mcp-server-langfuse-langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "mcp-server-langfuse-langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "mcp-server-langfuse-langfuse": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp-server-langfuse-langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "mcp-server-langfuse-langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-mcp-server-langfuse-langfuse"
      ]
    }
  }
}

FAQ

What is the MCP Server used for?

The MCP Server is used for managing and retrieving prompts in applications that utilize the Model Context Protocol.

Are there any limitations?

Yes, the server currently only returns prompts with a 'production' label and assumes all arguments are optional without descriptions.

How can I contribute?

Contributions are welcome! You can open an issue or a PR on the GitHub repository.

Developer tools