Production-ready Langfuse MCP Server with 28 tools for LLM analytics, cost monitoring, and dataset management. Features secure dual-mode operation (readonly & readwrite), real-time cost analysis, trace debugging, and comprehensive usage insights. Deploy instantly with npx for seamless Claude Desktop and other LLM Client integration.
Overview
What is Langfuse MCP?
Langfuse MCP is a production-ready server designed for LLM analytics, cost monitoring, and dataset management, featuring 28 powerful tools for comprehensive insights and management.
How to use Langfuse MCP?
To use Langfuse MCP, you can deploy it instantly using the command: npx @therealsachin/langfuse-mcp --readwrite. For Claude Desktop integration, configure the MCP server with the provided JSON structure.
Key features of Langfuse MCP?
- Real-time analytics for cost analysis and usage tracking.
- Dual security modes: Readonly and Readwrite with audit logging.
- Complete CRUD operations for dataset management.
- Advanced debugging tools for trace details and model insights.
- Cost optimization features to identify expensive traces and usage patterns.
Use cases of Langfuse MCP?
- AI teams managing costs and performance of LLMs.
- DevOps engineers monitoring production AI systems.
- Data scientists analyzing model usage patterns.
- Product teams optimizing AI feature costs.
FAQ from Langfuse MCP?
- Is Langfuse MCP suitable for production use?
Yes, it is built for production environments with enterprise-grade security features.
- How can I install Langfuse MCP?
You can install it using NPX or globally via npm.
- What security features does Langfuse MCP offer?
It includes HTTPS enforcement, audit logging, and pre-commit hooks for credential scanning.
Server Config
{
"mcpServers": {
"langfuse-mcp": {
"command": "npx",
"args": [
"langfuse-mcp"
],
"env": {
"LANGFUSE_SECRET_KEY": "<YOUR_LANGFUSE_SECRET_KEY>",
"LANGFUSE_PUBLIC_KEY": "<YOUR_LANGFUSE_PUBLIC_KEY>",
"LANGFUSE_HOST": "<YOUR_LANGFUSE_URL>"
}
}
}
}