MCP tools, A2A skills, and REST APIs — indexed, safety-scanned, and returned as a ready-to-invoke capability. Your agent asks in plain language; we hand back the endpoint, schema, and auth it needs to act.
Two endpoints. Search to discover, resolve to invoke.
POST /search with a natural-language query. Get back ranked
capabilities across MCP, A2A, and REST — each with a provider, protocol,
and safety status.
POST /resolve with a capability ID. Get back the live
endpoint, input/output schema, auth requirements, and payment hints —
everything needed to call it.
Every listed capability passes a static-analysis and LLM-classifier safety scan before it's ever served. Flagged capabilities go to human review, not to your agent.
Start free. Upgrade when your agent needs more resolves.
Unauthenticated search, plus 20 /resolve calls per day with an API key.
Higher resolve limits, payment-hint detail, and verified-provider filtering.
Everything in Starter, sized for high-volume agents. Talk to us for Enterprise.
Free tier, no credit card. You'll get a key back immediately.
Demo mode: billing/account issuance isn't live yet, so this
creates a placeholder key for trying out the form only — it won't authenticate
against the real /search or /resolve API.