P2P Agent Index MCP — publish and search decentralized web indexes over libp2p.
- capability exposure inferred + 14
- tool safety inferred + 7
- 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 2m ago · see ecosystem CVEs →
- A · 2 → A · 13
- A · 0 → A · 2
No known CVEs for this server.
- medium exfiltration combo get_network_setup
single tool reads + sends: fs, net
- low exfiltration combo search_index
single tool reads + sends: net, db
[](https://mcpobservatory.com/servers/github:agent-idx/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 agent-idx.