Categories › AI & Agents › Multi-agent, orchestration & workflows
Read only x402 catalogue: payability verdicts, prices, drift, host status, signatures. No wallet.
Remote server: your requests and data go to mcp.nsgoods.org. Claude Code: claude mcp add --transport http nsgoods-workbench-mcp https://mcp.nsgoods.org/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
payability_verdict — Latest payability observation for one exact resource URL (path and query included), with the meaning of the verdict, remediation if it cannofind_endpoints — Search the catalogue by host or URL substring. Returns up to `limit` endpoints (max 50) with their latest verdict, plus the total match councatalogue_stats — Size and health of the x402 catalogue as of the latest full scan: resources, hosts, verdict counts, and payable endpoints per network.host_summary — Summary for a host (no time series): first/last seen, current verdict mix, n_resources, total verdict changes, gone_since if absent from thex401_status — Current x401 emitter adoption across the scanned catalogue (from the daily watcher).drift_status — Verdict changes between the two latest full scans (catalogue wide, or for one host), plus the declared model drift watch.verify_signature — Offline EIP-191 verify of a signed nsgoods response. Identifies the service from the manifest (or the optional `service` arg), strips exactlreports — Published weekly payability reports (from the signed manifest).Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.