Persistent memory for AI assistants via MCP — semantic recall, knowledge graph, and a cockpit UI
- capability exposure inferred + 35
- recent drift inferred + 12
- tool safety inferred + 5
- trust mitigators mixed − 8
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 5m ago · see ecosystem CVEs →
- C · 49 → C · 44
- B · 32 → C · 49
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__()
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (jfr992-rekall-mcp-a117f92/ui/lib/a
analyzed commit a117f92 · analyzer v28 · 1d ago
skills & prompt files 10
- agent-rules jfr992-rekall-mcp-a117f92/CLAUDE.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-consolidate/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-observe/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-rebuild/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-recall/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-restore/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-skills/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/memory-stats/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/rekall-publish/SKILL.md
- skill jfr992-rekall-mcp-a117f92/claude/skills/rekall-setup/SKILL.md
danger signals1
- dynamic code execution __import__() jfr992-rekall-mcp-a117f92/tests/test_server_prune_superseded.py :145
__import__(
- recent drift +12 capability drift →
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 jfr992.