A local, offline second brain for coding agents: capture every session and every repo's docs, search them from any agent.
- capability exposure inferred + 26
- tool safety inferred + 12
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 1w ago · see ecosystem CVEs →
No known CVEs for this server.
- high dangerous code
committed secret: OpenAI key
analyzed commit f576d02 · analyzer v33 · 6d ago
skills & prompt files 1
- agent-rules alexeymohr-LexiconLocal-f576d02/CLAUDE.md
danger signals2
- suspicious endpoint 8.8.8.8 alexeymohr-LexiconLocal-f576d02/tests/test_pipeline.py :833
"http://8.8.8.8:11434", # public - committed secret OpenAI key alexeymohr-LexiconLocal-f576d02/tests/conftest.py :111
sk-zzz…(31 chars, redacted)
[](https://mcpobservatory.com/servers/github:alexeymohr/LexiconLocal/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 alexeymohr.