A
licenseA
qualityC
maintenanceComprehensive MCP server for Langfuse, enabling AI assistants to access and manage traces, observations, scores, datasets, and sessions for observability.
24
8 npm
1
MIT
langfuse-mcp
by avivsinai
Related Servers
Alternatives to langfuse-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityDmaintenanceModel Context Protocol server for Langfuse observability. Query traces, analyze accuracy, detect failures, track costs, debug latency, manage prompts and datasets.582MIT
- 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 gradedqualityBmaintenanceMCP server for Langfuse providing 50 tools for prompt management, observability, instance/organization management, and metrics tracking via natural language.19 npmMIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server for comprehensive monitoring and observability of systems using Langfuse.1MIT
- 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
C2.9/5.0
Scored across 48 tools
Disambiguation4/5
Most tools target clearly distinct resources or actions (traces, observations, sessions, datasets, prompts, queues). However, the exception/error cluster (find_exceptions, find_exceptions_in_file, get_exception_details, get_error_count) and the route-decision tools have overlapping scopes, and schema/resolved-prompt pairs are close enough to cause occasional misselection.
Naming Consistency3/5
All names use snake_case, but verbs are inconsistent across similar operations: fetch_traces/fetch_trace, get_session_details/get_user_sessions, and list_scores_v2/get_score_v2 mix fetch, get, and list. The _v2 suffixes and get_prompt_unresolved add further irregularity.
Tool Count2/5
48 tools is heavy for an MCP server and far exceeds the well-scoped 3–15 range. While Langfuse is a broad platform, the many CRUD variants for annotation queues, datasets, and route decisions make the surface unwieldy and risk overwhelming tool selection.
Completeness3/5
Coverage is broad across traces, observations, sessions, metrics, prompts, datasets, queues, and exceptions. But there are notable lifecycle gaps: scores are read-only (get/list, no create/update/delete), datasets lack delete/update at the dataset level, and annotation queues lack update/delete for the queue itself.
Maintenance
ActivityMaintained
ResponsivenessResponsive