Local-first MCP server for durable agent memory
- capability exposure inferred + 32
- recent drift inferred + 12
- tool safety inferred + 5
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.
graded 3m ago · see ecosystem CVEs →
- B · 32 → C · 49
- C · 35 → B · 32
- A · 4 → C · 35
- A · 10 → A · 4
No known CVEs for this server.
- medium dangerous code
dynamic exec: eval()/exec()
analyzed commit 20cccc4 · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules MK-986123-server-memory-20cccc4/AGENTS.md
danger signals1
- dynamic code execution eval()/exec() MK-986123-server-memory-20cccc4/tests/test_tools.py :1064
monkeypatch.setattr(server_module, "EmbeddingEngine", lambda model_name: exec("raise(RuntimeError('Embedding init failed'))"))
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:MK-986123/server-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 MK-986123.