A
licenseC
qualityA
maintenanceMCP server for Langfuse observability. Query traces, debug exceptions, analyze sessions, and manage prompts and datasets for your LLM applications.
48
3,403 PyPI
105
MIT
langfuse-mcp-extended
by JaviMaligno
Related Servers
Alternatives to langfuse-mcp-extended
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server for comprehensive monitoring and observability of systems using Langfuse.1MIT
- AlicenseNot gradedqualityBmaintenanceA read-only MCP server that enables agents to query and analyze Langfuse observability data, including traces, sessions, observations, scores, and metrics.MIT
- AlicenseNot gradedqualityAmaintenanceMCP server for Langfuse providing 50 tools for prompt management, observability, instance/organization management, and metrics tracking via natural language.10 npmMIT
- AlicenseCqualityCmaintenanceAn MCP server implementation that integrates AI assistants with Langfuse workspaces, allowing models to query LLM metrics by time range.18 npm3Apache 2.0
- AlicenseBqualityDmaintenanceMCP server for Langfuse that lets Claude Code create projects, manage API keys, and query traces without touching the web UI. Designed to work with a self-hosted Langfuse v3 stack running locally via Docker Compose.20MIT
TDQS
A3.6/5.0
Scored across 24 tools
Disambiguation5/5
Each tool targets a distinct resource-action pair (e.g., createDataset vs. createScore, listTraces vs. listScores). There is no ambiguity as resource types are clearly separated and operations are specific.
Naming Consistency5/5
All tools follow a strict verb+noun pattern (e.g., createDataset, getDatasetItem, listObservations) using snake_case consistently. No mixing of styles or vague verbs.
Tool Count5/5
24 tools cover the major resources (datasets, scores, traces, observations, sessions) with predictable CRUD operations. The count is well-scoped for a comprehensive observability server without being excessive.
Completeness3/5
The tool set lacks create endpoints for traces and observations, which are fundamental to the platform. While dataset items support upsert, the absence of trace and observation creation is a notable gap for a complete evaluation workflow.
Maintenance
ActivitySlowing
ResponsivenessUnresponsive