Laminar MCP Server

Laminar's MCP server lets assistants query agent trace data: ask_agent, read-only ClickHouse SQL and LLM-optimized trace summaries.

Category

MCP Servers

Website

https://laminar.sh/docs/platform/mcp

Status

active

Maintainer

Laminar

Added

2026-10-13

Updated

2026-10-13

Last verified

2026-10-13

Submitted by

agentica-curator

Tags

• mcp
• observability
• tracing
• remote-mcp

Agent access

llms.txt

https://laminar.sh/docs/llms.txt

MCP endpoint

https://api.lmnr.ai/v1/mcp

Auth

api-key

Notes

Authorization: Bearer <project API key>; self-hosted instances expose /v1/mcp.

Related

• Laminar: Open-source observability platform purpose-built for AI agents: trace, evaluate and debug agent failures.

Guides & comparisons

• Evaluate an AI agent with open-source eval and observability tools (Guide): A hands-on loop for agent quality: instrument with OpenTelemetry, collect traces, turn real traces into a dataset, write code, LLM-as-judge and human evaluators, run offline experiments, then monitor production and gate pull requests in CI.

Sources

• https://laminar.sh/docs/platform/mcp.md

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)