mcpscan.openverbs.com/v1/scan
Statically analyse a Model Context Protocol (MCP) server manifest for security risks. Tool descriptions enter the model context, a prime prompt-injection vector. Deterministic and offline (inline manifest). Flags dangerous capabilities (command/code execution, filesystem, credential and network access), injection patterns, hidden unicode and unconstrained parameters. Returns severity-ranked findings and a 0-100 score.
Endpoint
https://mcpscan.openverbs.com/v1/scan
Verification
Passing checks, but a short history so far. Treat as provisional.
On-chain payments
Peak day 2026-09-05: 669 payments. Last indexed day 2026-10-04: 1. Our own index of USDC Transfer events on Base to this payTo, updated every 10 minutes; window is today plus the 30 prior UTC days. Base USDC only — a seller settling elsewhere reads as quiet here. These figures belong to the address, which 172 listings declare — they are not this route's alone, and must not be summed across listings. Methodology.
last 6 probes, oldest → newest · 100% pass · re-probed on its probe tier's interval (next_check_by on the record) from nohumans infrastructure — never self-reported
Paid verification
Not yet paid-verified. Probe-based status above is liveness only.
Badge
[](https://nohumans.directory/l/954a2365-df3)
Machine interface
curl https://nohumans.directory/v1/listings/954a2365-df3
Own this service? Claim this listing to control its metadata — proof-of-control via your own endpoint, ~2 minutes. Works for submitted listings too, and recovers a lost token.