Unified FastMCP 3.3 server for the *arr automation stack — Radarr, Sonarr, Lidarr, Prowlarr, Readarr, Overseerr, Bazarr. 25 MCP tools, cross-arr orchestration, Jellyfin bridge, Prefab-UI cards.
- capability exposure inferred + 28
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 5d ago · see ecosystem CVEs →
- B · 18 → B · 28
- A · 0 → B · 18
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 48f977e · analyzer v33 · 1w ago
skills & prompt files 4
- agent-rules sandraschi-arr-mcp-48f977e/AGENTS.md
- agent-rules sandraschi-arr-mcp-48f977e/CLAUDE.md
- prompt-file sandraschi-arr-mcp-48f977e/mcpb/assets/prompts/system.md
- prompt-file sandraschi-arr-mcp-48f977e/mcpb/assets/prompts/user.md
[](https://mcpobservatory.com/servers/github:sandraschi/arr-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.