Persistent, trust-scored project memory for AI coding agents — MCP server + CLI, backed by PostgreSQL + pgvector.
- capability exposure inferred + 35
- tool safety inferred + 12
- abandonment inferred + 10
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 5d ago · see ecosystem CVEs →
- C · 47 → C · 57
- C · 35 → C · 47
No known CVEs for this server.
- high dangerous code
committed secret: GitHub token
analyzed commit 445011d · analyzer v33 · 3w ago
skills & prompt files 3
danger signals4
- committed secret GitHub token event4u-app-agent-memory-445011d/tests/unit/embedding-boundary.test.ts :25
ghp_01…(42 chars, redacted) - committed secret GitHub token event4u-app-agent-memory-445011d/tests/unit/logger-redact.test.ts :21
ghp_01…(42 chars, redacted) - committed secret GitHub token event4u-app-agent-memory-445011d/tests/unit/secret-guard-wiring.test.ts :26
ghp_01…(42 chars, redacted) - committed secret GitHub token event4u-app-agent-memory-445011d/tests/unit/secret-guard.test.ts :15
ghp_01…(42 chars, redacted)
- abandonment +10 abandonment hub →
[](https://mcpobservatory.com/servers/github:event4u-app/agent-memory/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of event4u-app.