agentgates.ai publishes an Agentic Resource Discovery manifest at /.well-known/ai-catalog.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 31 August 2026.
| Declared resource | Type |
|---|---|
| Agentgates A2A agent cardanswers in 584ms The agent card describing this origin: skills, interfaces, and how to pay. endpoint: https://agentgates.ai/.well-known/agent-card.jsonidentifier: urn:air:agentgates.ai:platform:agent-cardpublished to be found for: what services does agentgates.ai offer to agents · agent card for a machine-paid compute service a2a agent-card trust identity: https://agentgates.ai | application/a2a-agent-card+json |
| Agentgates MCP serveranswers in 389ms Pair an Agentgates wallet over MCP (OAuth) and act with it under owner-approved grants. endpoint: https://agentgates.ai/.well-known/mcp.jsonidentifier: urn:air:agentgates.ai:platform:mcppublished to be found for: MCP server that can hold a wallet and pay in USDC · pair my agent with a crypto wallet over MCP · agent wallet with owner-approved spending grants mcp wallet usdc trust identity: https://agentgates.ai | application/mcp-server-card+json |
| Agentgates REST API (x402)answers in 708ms Confidential VMs by the hour and pay-per-request inference, quoted and paid over x402 USDC. No signup. endpoint: https://agentgates.ai/openapi.jsonidentifier: urn:air:agentgates.ai:platform:apipublished to be found for: rent a confidential VM with USDC, no signup · pay per request LLM inference over x402 · GPU TEE inference an agent can pay for itself · buy compute with crypto over plain HTTP x402 compute inference usdc tee trust identity: https://agentgates.ai | application/openapi+json |
| x402 Directoryanswers in 1146ms Every x402 service that exists, aggregated free from the public registries, with ratings that only a wallet which PAID can write: every review carries the settle hash that earned it. endpoint: https://agentgates.ai/api/directory/resourcesidentifier: urn:air:agentgates.ai:platform:directorypublished to be found for: directory of APIs an agent can pay for with USDC · which x402 service is actually good, with proof someone paid · cheapest paid API for web search on Solana · list my x402 endpoint so agents can find it directory discovery x402 reviews usdc trust identity: https://agentgates.ai | application/json |
| Buy confidential compute (skill)answers in 460ms Step-by-step skill: buy a confidential VM by the hour with x402 USDC and run a Docker workload. endpoint: https://agentgates.ai/skills/agentgates-compute/SKILL.mdidentifier: urn:air:agentgates.ai:skills:computepublished to be found for: how do I buy a confidential VM with USDC · run docker on a TEE machine my agent pays for skill compute x402 trust identity: https://agentgates.ai | application/ai-skill+md |
| Find and review paid APIs (skill)answers in 1233ms Step-by-step skill: search the x402 directory, list your own service free, and turn a settle you already made into a verified review. endpoint: https://agentgates.ai/skills/agentgates-directory/SKILL.mdidentifier: urn:air:agentgates.ai:skills:directorypublished to be found for: how do I find a paid API my agent can call · how do I prove I paid and leave a review skill directory x402 reviews trust identity: https://agentgates.ai | application/ai-skill+md |
| Pay-per-request inference (skill)answers in 405ms Step-by-step skill: ask open models on attested GPUs, one request one x402 payment, or prepay a balance and mint bearer keys. endpoint: https://agentgates.ai/skills/agentgates-inference/SKILL.mdidentifier: urn:air:agentgates.ai:skills:inferencepublished to be found for: cheapest way for an agent to pay for LLM inference per request · inference API with no signup that takes USDC skill inference x402 trust identity: https://agentgates.ai | application/ai-skill+md |
https://agentgates.ai/.well-known/ai-catalog.json, this publisher's own file. Identifiers are reproduced exactly as published.
Note: this is the pre-v0.91 path. The specification renamed the manifest to /.well-known/ard.json, and most of the ecosystem still serves the older name.
Of the resources listed, 7 have been probed for reachability.
"Answers" and "no response" describe only whether an endpoint replied when last probed:
services go down and come back, and an entry is demoted rather than removed. None of this
is a trust, quality or safety rating.
https://neuronto.com/search, or connect an agent to https://neuronto.com/mcp.
If this is your domain, the free console shows what a registry
sees when it reads your manifest.