Local-first AI assistant with Multi-LLM backends, MCP tool servers, autonomous execution. Web UI + CLI. What you see is just the tip of the iceberg.
- capability exposure inferred + 35
- recent drift inferred + 12
- 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 2h ago · see ecosystem CVEs →
- D · 67 → C · 59
- C · 59 → D · 67
- C · 47 → C · 59
- C · 59 → C · 47
- D · 67 → C · 59
- C · 59 → D · 67
- A · 0 → C · 59
No known CVEs for this server.
- high dangerous code
committed secret: Slack token
- medium dangerous code
env-secret-flows-to-network-py: An environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a key, call
analyzed commit 1438011 · analyzer v33 · 1d ago
skills & prompt files 1
- agent-rules Forbidden0005-Project-Iceberg-1438011/CLAUDE.md
danger signals1
- committed secret Slack token Forbidden0005-Project-Iceberg-1438011/tools/mcp_catalog.py :108
xoxb-y…(19 chars, redacted)
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:Forbidden0005/Project-Iceberg/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 Forbidden0005.