Langfuse Prompt Management
FreeLangfuse 官方集成，用于协作编辑、版本控制、评估和发布提示的开源工具。(已在开发工具部分列出)
FreeFree tier
About Langfuse Prompt Management
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. It implements the MCP Prompts specification for prompt discovery and retrieval, and also exports tools for clients that do not support the prompt capability. Supports cursor-based pagination, transforms Langfuse prompts (text and chat) into MCP prompt objects, and compiles prompts with provided variables.
Key Features
Implements MCP Prompts specification (prompts/list and prompts/get) with cursor-based pagination
Transforms Langfuse prompts (text and chat) into MCP prompt objects and compiles with variables
Exports tools (get-prompts and get-prompt) for MCP clients without native prompt capability
Returns only prompts with a production label from Langfuse
Easy integration with Claude Desktop, Cursor, and other MCP-compatible clients
Pros & Cons
Pros
- Official Langfuse integration for prompt management
- Supports both MCP prompts and tools for wider client compatibility
- Enables collaborative editing, version control, and evaluation of prompts through Langfuse backend
- Open source with clear setup instructions for popular clients
Cons
- Only prompts with a production label in Langfuse are returned
- All prompt arguments are assumed to be optional and lack descriptions
- List operations fetch each prompt individually, which is inefficient for many prompts
- Work in progress with limited features and contributions welcome
Best For
Retrieving and managing Langfuse prompts from AI assistants like Claude DesktopIntegrating Langfuse prompt version control and evaluation into MCP-based workflowsProgrammatically compiling prompts with dynamic variables for LLM interactionsDiscovering available prompts and their required arguments via MCP protocol
FAQ
What is the Langfuse Prompt Management MCP Server?
It is an open-source server that implements the Model Context Protocol (MCP) to allow AI clients like Claude Desktop to access and manage Langfuse prompts.
How do I set it up with Claude Desktop?
Build the server with npm install && npm run build, then add it to claude_desktop_config.json with your Langfuse API keys as environment variables.
What are the limitations of this server?
Only prompts with a production label are returned, arguments are assumed optional and lack descriptions, and list operations are inefficient as they fetch each prompt individually.