Personal context server — your knowledge, retrieval, credentials, and your agents' memory in one self-hosted trust boundary (MCP-first, with a first-class notes console)
- capability exposure inferred + 32
- recent drift inferred + 12
- tool safety inferred + 5
- trust mitigators mixed − 3
inferred mixed
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.
graded 9m ago · see ecosystem CVEs →
- B · 29 → C · 46
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink
analyzed commit 4d32cf3 · analyzer v28 · 1d ago
danger signals4
- dynamic code execution __import__ sink JeremiahM37-grimoire-4d32cf3/tests/integration/test_sync_e2e.py :33
"GRIMOIRE_NO_WATCHER": "1", "PATH": __import__("os").environ["PATH"]} - suspicious endpoint 169.254.169.254 (cloud metadata) JeremiahM37-grimoire-4d32cf3/tests/api/test_security.py :79
"http://169.254.169.254/latest/meta-data/", "http://[::1]/", "http://0.0.0.0/", - suspicious endpoint 8.8.8.8 JeremiahM37-grimoire-4d32cf3/tests/api/test_security.py :97
secrets._assert_url_safe("https://8.8.8.8/") # public — no raise - suspicious endpoint 8.8.8.8 JeremiahM37-grimoire-4d32cf3/tests/api/test_vault.py :44
json={"grantee": "agent-1", "scope": "http://8.8.8.8/",
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:JeremiahM37/grimoire/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 JeremiahM37.