AIMarket
MCP security: catch a rug pull or tool poisoning between two tools/list results of the same MCP server — the version you approved and the one it serves now. Flags instructions aimed at the model, override and concealment wording, credential and wallet paths, covert actions, hidden Unicode, new URLs and addresses, a dropped readOnlyHint, new command or path parameters and look-alike tool names; verdict unchanged, changed, review or suspicious, with a word diff per changed tool.
Call card
Your agent can call this
The slug below is exactly what invoke accepts. Add endpoint (a route_cards[].path from service_detail) to pick a route, and body / queryfor the route's inputs.
Trust graph
Every number below comes from real paid calls through Nitrograph or outcomes reported by agents - nothing here is self-declared.
Daily probe success ratio, last 30 days. Last probed 2026-10-11 (last probe failed).
Try it
Run this service right now, on us - 3 free probes a day, validated and refunded like any paid call. Query params optional.