REA
Verified · 33 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
MCP server for Langfuse LLM observability — trace and observation analysis.
claude mcp add langfuse -- npx -y [email protected]
Read-only Langfuse trace inspection: four tools (get_traces, get_trace_detail, get_observations, get_observation) for debugging LLM pipelines and analyzing cost/latency, with a practical token-saving touch — any payload field over 1000 chars is truncated to a /tmp file with a grep-able reference. It requires Langfuse public and secret keys and defaults to Langfuse Cloud, though self-hosted instances work via LANGFUSE_BASE_URL. Like the remote-filesystem sibling it lives in the 'experimental' tier of PulseMCP's monorepo — explicitly not graduated to their productionized set — and adoption is thin (~73 weekly downloads). For teams already on Langfuse who want an agent to dig through traces; the read-only design keeps the blast radius small.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.