avivsinai/langfuse-mcp
If you are the rightful owner of langfuse-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Langfuse MCP (Model Context Protocol) server facilitates AI agents in querying Langfuse trace data for enhanced debugging and observability.
Langfuse MCP is a server designed to integrate with Langfuse, providing AI agents with the ability to query trace and observation data. This server is particularly useful for debugging and monitoring AI models by offering a suite of tools that can fetch traces, observations, and session details. It supports exception and error tracking, making it easier to identify and resolve issues within AI systems. The server is compatible with various platforms and can be configured to work with different environments, ensuring flexibility and adaptability in diverse setups. With its robust feature set, Langfuse MCP enhances the observability of AI models, providing insights into their performance and behavior.
Features
- Integration with Langfuse for trace and observation data
- Tool suite for AI agents to query trace data
- Exception and error tracking capabilities
- Session and user activity monitoring
- Configurable output modes for detailed responses
Tools
fetch_traces
Find traces based on criteria like user ID, session ID, etc.
fetch_trace
Get a specific trace by ID
fetch_observations
Get observations filtered by type
fetch_observation
Get a specific observation by ID
fetch_sessions
List sessions in the current project