FastMCP Bluesky / AT Proto client with SOTA webapp and a human-approved outbox for fleet promotion drafts. Dry-run by default.
- capability exposure inferred + 35
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 6d ago · see ecosystem CVEs →
- B · 32 → C · 35
No known CVEs for this server.
- low 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 83e326b · analyzer v33 · 1w ago
skills & prompt files 9
- agent-rules sandraschi-bluesky-mcp-83e326b/.cursorrules
- agent-rules sandraschi-bluesky-mcp-83e326b/.github/copilot-instructions.md
- skill sandraschi-bluesky-mcp-83e326b/.opencode/skills/session-context/SKILL.md
- agent-rules sandraschi-bluesky-mcp-83e326b/.windsurfrules
- agent-rules sandraschi-bluesky-mcp-83e326b/AGENTS.md
- agent-rules sandraschi-bluesky-mcp-83e326b/CLAUDE.md
- prompt-file sandraschi-bluesky-mcp-83e326b/assets/prompts/system.md
- prompt-file sandraschi-bluesky-mcp-83e326b/assets/prompts/user.md
- skill sandraschi-bluesky-mcp-83e326b/src/bluesky_mcp/skills/bluesky-outbox/SKILL.md
[](https://mcpobservatory.com/servers/github:sandraschi/bluesky-mcp/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 sandraschi.