metabrain
MCP server giving AI agents persistent SQLite memory that proves which lessons hold.
Connector by ariaxhan · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/ariaxhan-metabrain
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 3 read · 3 write · 0 delete · 1 not yet classified
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Python package
Tools by what they do 7
Read from the source code; the running server may list different tools.
Read 3 · Look things up without changing anything.
hypothesesrecallstats
Write 3 · Create, change, send or run things.
learnstart_briefverdict
Not yet classified 1 · We could not tell from the name and description.
capture_error
Tools (7)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
capture_errorRecord a failure from `tool` name, `error` text, and optional `context`, returning the stored error entry.
hypothesesList hypothesis objects, optionally filtered by `status` (testing, graduated, or rejected).
learnRecord or reinforce one lesson from `type` (failure, pattern, gotcha, or preference), `insight`, and optional `domain` and `context`, returning the stored lesson.
recallSearch stored lessons for the substring `query` and return up to `limit` matching lesson objects, newest first.
start_briefReturn the start-of-task digest (preferences, learnings, open_hypotheses, open_units, last_checkpoint, recent_errors), taking no arguments.
statsReturn a mapping of every metabrain table name to its row count, taking no arguments.
verdictRecord `result` ("pass" or "fail") against an optional `unit` or `hypothesis` with optional `evidence`, and return the stored entry (an experiment is written when a hypothesis is in play).
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 37
- Last commit
- Aug 26, 2026 (2 months ago)
- Last release
- Aug 26, 2026 (2 months ago)
- Last package publish
- Aug 26, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.ariaxhan/metabrain- Version
- 1.1.2
- Auth
- No auth
- Packages
- pypi metabrain
- License
- MIT
- Repository
- github.com/ariaxhan/metabrain
- First seen
- Oct 24, 2026
- Last checked
- Oct 25, 2026
More from ariaxhan
- 0.578score

Thinking Brain School — Teaching MCP
ariaxhan
Guided practice with Thinking Brain School lessons your family has unlocked, inside your AI app.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.510score
agentmailkit
ariaxhan
Run scheduled LLM-written email digests from local files and feeds.
ConnectorBFreshness: BLocal★ 1↓ 69/wkClaude Code +5 - 0.475score
site-spec
ariaxhan
MCP server: audit any website for SEO, accessibility, and AI-searchability, then auto-fix it.
ConnectorBFreshness: BLocal★ 1Claude Code +5
Cite this page
metabrain MCP server. Agent Mart. https://agentmart.dev/connectors/ariaxhan-metabrain (last updated 2026-10-25)