Metis MCP server
Governed tacit memory for AI agents: reviewed expert know-how, given only where conditions match
2 stars
Reviews
Write oneNobody has reviewed Metis yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Metis tools
No tool declarations could be read from the package source. They show once the server is installed.
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- Code scan144 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 9 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
How Metis compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 94/100
- higher than 96% of 48,255 servers
- GitHub stars
- 2
- more than 75% of 28,688 servers
Install Metis in Claude Code, Cursor or VS Code
claude mcp add metis -- uvx metis-memory
What the publisher says
From the Metis repository's README, as published. We do not edit it. Read it on GitHub
Website · Documentation · Paper · PyPI · CHAP
<!-- mcp-name: io.github.BrightbeamAI/metis -->
Metis is an open-source toolkit for capturing fragments of expert practice and making them available to AI agents as memory, with human review and agreed conditions for use.
Tacit fragments: a fourth layer of agent memory
A tacit fragment records what an expert noticed, how they responded, and the circumstances of that response. After human review, it sits alongside procedures, facts, and past events in the agent's memory.
The gap between procedure and practice
Procedures describe what should happen, and logs record what happened. The cue behind an expert's decision, and the reason for it, often go unrecorded.
How a fragment reaches an agent
Every capture, confirmation, review decision, and retrieval is recorded through the CHAP reference coordinator, chap-coordinator, on a hash-linked evidence chain.
The capture loop
When a recorded action differs from the procedure, a capture agent asks the expert one short question, a whisper, and the expert confirms the account in their own words.
Seventeen kinds of know-how
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Metis: common questions
- Is Metis MCP server safe?
- Yes, by our scan: it is graded A (94/100). Read the Metis safety report
- How do I install Metis?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Metis need an API key?
- No secret keys are declared. It reads 1 setting from the environment.
- Is Metis maintained?
- The last commit was 30 days ago (2026-10-05). The latest release is v0.1.6.
- How does Metis compare with other MCP servers?
- safety score 94/100 (higher than 96% of 48,255 servers); github stars 2 (more than 75% of 28,688 servers). Full comparison.