Langfuse Prompt Management

v1.0.0Developer Toolsstable

Facilitates access and management of Langfuse prompts through the Model Context Protocol, enabling prompt discovery, retrieval, and integration within clients like Claude Desktop and Cursor.

langfusellmllmopsmcpmodel-context-protocol
Share:
167
Stars
0
Downloads
0
Weekly
0/5

What is Langfuse Prompt Management?

Langfuse Prompt Management is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to facilitates access and management of langfuse prompts through the model context protocol, enabling prompt discovery, retrieval, and integration within clients like claude desktop and cursor.

Facilitates access and management of Langfuse prompts through the Model Context Protocol, enabling prompt discovery, retrieval, and integration within clients like Claude Desktop and Cursor.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Facilitates access and management of Langfuse prompts throug

Use Cases

Access and manage Langfuse prompts
Prompt discovery and integration
LLMOps automation
langfuse

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx langfuse-prompt-management-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Langfuse Prompt Management

The Langfuse Prompt Management MCP Server connects AI clients like Claude Desktop and Cursor directly to your Langfuse prompt library, enabling discovery, retrieval, and compiled rendering of production-tagged prompts stored in Langfuse. It exposes both native MCP prompt endpoints (prompts/list, prompts/get) and tool-based equivalents (get-prompts, get-prompt) for maximum client compatibility, so you can pull versioned, production-ready prompt templates into any conversation without switching to the Langfuse UI.

Prerequisites

  • A Langfuse account (cloud at cloud.langfuse.com or self-hosted instance)
  • Langfuse Public Key and Secret Key from your project settings
  • Node.js 18 or higher and npm installed
  • An MCP client such as Claude Desktop or Cursor
1

Clone and install the MCP server

Clone the mcp-server-langfuse repository and install its Node.js dependencies.

git clone https://github.com/langfuse/mcp-server-langfuse.git
cd mcp-server-langfuse
npm install
2

Build the TypeScript server

Compile the TypeScript source to JavaScript. The output will be placed in the dist/ directory.

npm run build
3

Obtain your Langfuse API keys

Log into your Langfuse project, navigate to Settings > API Keys, and copy your Public Key and Secret Key. If you are self-hosting Langfuse, also note your custom base URL.

4

Configure Claude Desktop with credentials

Add the server entry to your claude_desktop_config.json, providing your Langfuse keys as environment variables. LANGFUSE_BASEURL defaults to cloud.langfuse.com if omitted.

{
  "mcpServers": {
    "langfuse": {
      "command": "node",
      "args": ["/path/to/mcp-server-langfuse/dist/index.js"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-...",
        "LANGFUSE_SECRET_KEY": "sk-lf-...",
        "LANGFUSE_BASEURL": "https://cloud.langfuse.com"
      }
    }
  }
}
5

Tag prompts as production in Langfuse

Only prompts with the 'production' label in Langfuse are accessible via the MCP server. In your Langfuse project, open each prompt you want exposed and promote it to the production label.

6

Restart Claude Desktop and test

Restart Claude Desktop to load the server. Ask Claude to list available prompts to confirm the connection is working.

Langfuse Prompt Management Examples

Client configuration

Claude Desktop configuration for the Langfuse Prompt Management MCP server using the compiled Node.js entry point.

{
  "mcpServers": {
    "langfuse": {
      "command": "node",
      "args": ["/path/to/mcp-server-langfuse/dist/index.js"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "pk-lf-your_public_key",
        "LANGFUSE_SECRET_KEY": "sk-lf-your_secret_key",
        "LANGFUSE_BASEURL": "https://cloud.langfuse.com"
      }
    }
  }
}

Prompts to try

Example prompts to use once the Langfuse MCP server is connected and your production prompts are tagged.

- "List all available prompts in my Langfuse project"
- "Get the prompt named 'customer-support-reply' and compile it with these variables: customer_name='Alice', issue='billing'"
- "What prompts do I have available for email generation?"
- "Retrieve the 'code-review' prompt from Langfuse and apply it to my function"
- "Show me the next page of prompts after cursor xyz"

Troubleshooting Langfuse Prompt Management

No prompts appear even though you have prompts in Langfuse

Only prompts with the 'production' label in Langfuse are returned by the MCP server. Open each prompt in Langfuse, go to its versions, and promote at least one version to the 'production' label.

Authentication fails with 401 Unauthorized

Double-check that LANGFUSE_PUBLIC_KEY starts with 'pk-lf-' and LANGFUSE_SECRET_KEY starts with 'sk-lf-'. Ensure both belong to the same Langfuse project. For self-hosted deployments, verify LANGFUSE_BASEURL matches your instance URL exactly, without a trailing slash.

Server fails to start after npm run build

Ensure you are using Node.js 18 or higher ('node --version'). If the build fails with TypeScript errors, run 'npm install' again to ensure all devDependencies including the TypeScript compiler are installed.

Frequently Asked Questions about Langfuse Prompt Management

What is Langfuse Prompt Management?

Langfuse Prompt Management is a Model Context Protocol (MCP) server that facilitates access and management of langfuse prompts through the model context protocol, enabling prompt discovery, retrieval, and integration within clients like claude desktop and cursor. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Langfuse Prompt Management?

Follow the installation instructions on the Langfuse Prompt Management GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Langfuse Prompt Management?

Langfuse Prompt Management works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Langfuse Prompt Management free to use?

Yes, Langfuse Prompt Management is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "langfuse-prompt-management-mcp-server": { "command": "npx", "args": ["-y", "langfuse-prompt-management-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Langfuse Prompt Management?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides