langfuse-mcp
Verified Safeby avivsinai
Overview
Provides a comprehensive Model Context Protocol (MCP) server for Langfuse, enabling AI agents to debug, analyze, and manage AI traces, observations, sessions, exceptions, and prompts.
Installation
uvx --python 3.11 langfuse-mcp --public-key YOUR_KEY --secret-key YOUR_SECRET --host https://cloud.langfuse.comEnvironment Variables
- LANGFUSE_PUBLIC_KEY
- LANGFUSE_SECRET_KEY
- LANGFUSE_HOST
- LANGFUSE_TIMEOUT
- LANGFUSE_MCP_TOOLS
- LANGFUSE_MCP_LOG_FILE
- LANGFUSE_LOG_LEVEL
- LANGFUSE_LOG_TO_CONSOLE
Security Notes
The server handles sensitive Langfuse API keys (Public, Secret), which are expected to be securely provided via environment variables or configuration files, not hardcoded. The `full_json_file` output mode can export sensitive AI trace data to the local filesystem (defaulting to `/tmp/langfuse_mcp_dumps`), which requires user awareness for data handling and storage location. The `SECURITY.md` outlines responsible disclosure. No direct code vulnerabilities like `eval` or arbitrary command injection are apparent; interactions are primarily with the Langfuse API.
Similar Servers
mcp-shark
Aggregate multiple Model Context Protocol (MCP) servers into a single unified interface with a powerful monitoring UI.
1xn-vmcp
An open-source platform for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, enabling fine-grained context engineering for AI workflows and agents.
tenets
Provides intelligent, token-optimized code context and automatically injects guiding principles to AI coding assistants for enhanced understanding and consistent interactions.
mcp-ai-agent-guidelines
A comprehensive AI agent development framework focused on structured design, prompt engineering, code analysis, and agent-to-agent orchestration for developers.