MetatronSAFE
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving laye
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
▶ Watch the 2-minute demo — files-first mode (default)
🎬 Also available: the MCP serving-layer mode demo.
Metatron captures a codebase's real implementation decisions — preferred patterns, rejected approaches, edge cases, internal conventions — as structured decisions: one markdown file per convention, versioned in git next to the code, consulted by any coding agent that can
e4de1c0aa072OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add metatron-webui --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"metatron-webui": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_verification_template | read | Return the canonical verification-contract skeleton, so you can draft a new |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (19)
return hashlib.sha1(email.strip().lower().encode("utf-8")).hexdigest()[:12] if email else ""digest = hashlib.sha1(id_str.encode("utf-8")).hexdigest()[:6]return hashlib.sha1(
return hashlib.sha1(
digest = hashlib.sha1(repo_id.encode("utf-8")).hexdigest()[:6]Metatron curation UI on http://127.0.0.1:1337 (Ctrl-C to stop)
yield store, decision, f"http://127.0.0.1:{port}"base = f"http://127.0.0.1:{port}"yield fm, f"http://127.0.0.1:{port}"with urllib.request.urlopen(f"http://127.0.0.1:{port}/api/mode") as r:-d '{"email":"[email protected]","password":"Correct123!"}'-d '{"email":"[email protected]","password":"wrong"}'-d '{"email":"[email protected]","password":"Correct123!"}'-d '{"email":"[email protected]","password":"wrong"}'assets/metatron-banner-hdr.png
You are a senior engineer turning a piece of feedback — a convention a coding agent
You are a senior engineer reviewing candidate "decisions" — proposed conventions for a
Ingest a repo (mount it read-only and pass your API key), curate, then serve:
curl -sSf https://getmetatron.com/install.sh | sh
Gates applied: no_behavioural_pass.
e4de1c0aa072full audit observations/trust-audit/mcp-server/kerbelp__metatron.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | e4de1c0aa072 | SAFE | B | 88 | first audit |
Questions
What is the Metatron MCP server?
Git-native context layer for AI coding agents. Your team's real engineering decisions — patterns, pitfalls, conventions — live as reviewed markdown files in your repo; agents consult them before writing code and record what they learn. Files-first, no server required; MCP as an optional serving laye
What tools does Metatron expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Metatron safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Metatron need?
It reads ANTHROPIC_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (e4de1c0aa072), read on 2026-10-09. The repository is watched and re-audited when it changes.