mach-agent-lab-edge.vercel.app publishes an Agentic Resource Discovery manifest at /.well-known/ard.json, declaring what an AI agent can call on this domain. Everything below is read from that file. First seen by our crawler on 23 September 2026.
| Declared resource | Type |
|---|---|
| MACH Agent Lab Edgeanswers in 363msv0.4.0 Production-disconnected A2A agent for testing autonomous capability discovery and selection. It exposes deterministic lab-only skills and cannot execute MACH production services or make payments. endpoint: https://mach-agent-lab-edge.vercel.app/.well-known/agent-card.jsonidentifier: urn:air:mach-agent-lab-edge.vercel.app:agent:mach-agent-lab-edgepublished to be found for: find a lab-only A2A agent for capability discovery · test how an AI agent discovers external capabilities · find an A2A agent for tool selection experiments a2a agent-discovery lab-only deterministic production-disconnected tool-selection json-normalize url-classify | application/a2a-agent-card+json |
| MACH Agent Lab MCPanswers3 verified toolsv0.1.0 Read-only lab MCP exposing deterministic JSON normalization, URL classification, and EVM address-format validation. endpoint: https://mach-agent-lab-edge.vercel.app/api/mcp/server-cardidentifier: urn:air:mach-agent-lab-edge.vercel.app:mcp:mach-agent-lab-mcppublished to be found for: normalize JSON with a verified MCP tool · classify a URL without fetching with MCP · validate EVM wallet address format without RPC mcp read-only deterministic lab-only no-production normalize_json classify_url_without_fetchin validate_evm_wallet_address_ | application/mcp-server-card+json |
| app.vercel.mach-agent-lab-edge/mcpanswers3 verified tools MCP server at mach-agent-lab-edge.vercel.app, verified by introspection: 3 tools exposed. endpoint: https://mach-agent-lab-edge.vercel.app/api/mcpidentifier: urn:air:mach-agent-lab-edge.vercel.app:mcp:app-vercel-mach-agent-lab-edge-mcp | application/mcp-server-card+json |
| Classify URL without fetchinganswers in 306msv0.1.0 Classify a URL string locally into a routing category without browsing, fetching, DNS lookup or outbound network access. endpoint: https://mach-agent-lab-edge.vercel.app/skills/classify-url-intent.mdidentifier: urn:air:mach-agent-lab-edge.vercel.app:skill:classify-url-intentpublished to be found for: classify a URL without fetching · classify this URL string without making a network request · identify whether a string is a web URL or git repository · route a URL string locally without browsing url classification routing no-network deterministic lab-only url-classification intent-routing | application/ai-skill+md |
| Normalize JSONanswers in 340msv0.1.0 Deterministically normalize a JSON object into stable key order for comparison, validation and structured-data workflow tests. endpoint: https://mach-agent-lab-edge.vercel.app/skills/normalize-json.mdidentifier: urn:air:mach-agent-lab-edge.vercel.app:skill:normalize-jsonpublished to be found for: normalize this JSON into a stable deterministic structure · make JSON key order deterministic · prepare JSON for deterministic comparison json normalize validation structured-data deterministic lab-only json-normalize json-validation | application/ai-skill+md |
| Validate EVM wallet address formatanswers in 332msv0.1.0 Validate the local string format of an EVM-style 0x wallet address without RPC, blockchain lookup, balance query or transaction. endpoint: https://mach-agent-lab-edge.vercel.app/skills/validate-evm-wallet-format.mdidentifier: urn:air:mach-agent-lab-edge.vercel.app:skill:validate-evm-wallet-formatpublished to be found for: check an Ethereum wallet address format without RPC · validate a 0x address string without querying a blockchain · check EVM address formatting locally evm wallet address validation no-rpc blockchain lab-only evm-address-validation | application/ai-skill+md |
https://mach-agent-lab-edge.vercel.app/.well-known/ard.json, this publisher's own file. Identifiers are reproduced exactly as published.
Of the resources listed, 6 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.