FastMCP 3.2 server for AI agents to issue verbal commands to Alexa devices
- capability exposure inferred + 10
- tool safety inferred + 5
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 · 33 → B · 15
- A · 10 → B · 33
- A · 6 → A · 10
No known CVEs for this server.
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tool + source surface: private-data access + untrusted-content ingestion + network exfil (a leg is proven only in the analyzed source)
analyzed commit f8a4904 · analyzer v33 · 1w ago
skills & prompt files 8
- agent-rules sandraschi-alexa-mcp-f8a4904/.cursorrules
- agent-rules sandraschi-alexa-mcp-f8a4904/.github/copilot-instructions.md
- agent-rules sandraschi-alexa-mcp-f8a4904/.windsurfrules
- agent-rules sandraschi-alexa-mcp-f8a4904/AGENTS.md
- agent-rules sandraschi-alexa-mcp-f8a4904/CLAUDE.md
- prompt-file sandraschi-alexa-mcp-f8a4904/mcpb/assets/prompts/system.md
- prompt-file sandraschi-alexa-mcp-f8a4904/mcpb/assets/prompts/user.md
- skill sandraschi-alexa-mcp-f8a4904/src/alexa_mcp/skills/alexa-bridge/SKILL.md
[](https://mcpobservatory.com/servers/github:sandraschi/alexa-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.