Skip to content
Back to search
A2A

AgentShopping

agentshopping.org

Machine-readable buyer-intent catalog and supply discovery for AI agents. Covers 100 common transaction intents. No funds pass through this service.

Sign in to save Compare Sign in to watch
1 thing in this card we could not use
Everything else was indexed. Fix the card at https://agentshopping.org/.well-known/agent-card.json and the next probe clears this panel.
Field What we saw What we stored
capabilities Input should be a valid dictionary or instance of Capabilities dropped — this field was not indexed
Conformance
24/100
grade F · 9 criteria
Uptime
Collecting
1/5 direct probes · 30d
~136 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →
F
Conformance score: 24/100
F-grade: card is reachable but fails most operational signals.
Show breakdown Hide breakdown

Respond live on JSON-RPC · 20 points available for live json-rpc

partial Valid AgentCard 9/10
AgentCard did not read cleanly: 1 field we could not read. Scored on what we could read, not on a card that arrived as published — the card findings name every affected field and what we did with it.
How to earn +1 point
Publish a parseable A2A AgentCard
Serve a valid AgentCard JSON at /.well-known/agent-card.json. The A2A 1.0 schema is the reference; we accept the v0.x backwards-compatible variant too.
Docs
fail Live JSON-RPC 5/25
Endpoint replies but body isn't a valid JSON-RPC 2.0 A2A response.
How to earn +20 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs
fail Protocol version 0/10
No protocolVersion in card.
How to earn +10 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs
info JWS signature 0/10
Card is unsigned (most published agents are).
info Uptime track record 0/15
Only 1 probe so far, need ≥5 for an uptime grade.
partial Skill declaration 6/10
Declares 1 skill, usable but thin.
How to earn +4 points
Declare your skills
Add at least one entry to the `skills` array on the AgentCard, each with `id`, `name`, `description`, `tags` — `description` and `tags` are REQUIRED on AgentSkill since A2A v1.0, and tags are what discovery filters match on. We canonicalise these into the global skill taxonomy on next probe.
Docs
fail Verified Identity 0/10
No provider organisation declared. Anonymous agent.
How to earn +10 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs
pass Freshness + modern flags 4/5
seen in upstream source within 0d
info Security declaration 0/5
Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.

Activity

last 24h · 0 invocations No personal data recorded

No activity in the last 7 days.

Card history

1 snapshot
Snapshots
Agent card snapshots
Captured Hash Snapshot
2026-11-16 22:46:06 current dd08a9844a1f… view →
Uptime
accumulating
1 direct probes · 30d
Response
124ms
last direct probe
Skills
0
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://agentshopping.org/.well-known/agent-card.json
Discovered via
manifests

Skills · 1 declared

AgentShopping

Machine-readable buyer-intent catalog and supply discovery for AI agents. Covers 100 common transaction intents. No funds pass through this service.

No taxonomy category yet

Health · last 1 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-16 22:46:06 200 ✗ 124ms

Similar agents

SearchShopAI live
Commerce capability layer for AI agents. Product search, domain-expert recommendations, and checkout. Multi-tenant, multi-protocol.
q 92%
AgentUtil Docs
Instant documentation search for AI agents. 10 platforms pre-indexed (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, Next.js, Tailwind, htm
AgentUtil · q 66%
Agentcard
Agentcard lets your AI agent buy anything online for your users: Vault for each user's own saved card, Issuing for cards the agent spends as
Agentcard · q 90%
Agenticfeed Product Query Agent
Query structured ecommerce product data by natural language buyer intent. Returns schema.org Product ItemList matched to the buyer's need, w
q 62%
Butiful Agent Commerce
Agent-ready commerce for Butiful. AI agents can browse products, request Shopify-priced quotes, and purchase physical products using x402/US
agent.butiful.org · q 65%
Agent Decision Engine
Machine-readable intelligence layer for AI agent purchasing decisions. Trust scores, vendor recommendations, outcome predictions, AND a full
decide.memoryapi.org · q 57%
Embed a badge

Updates itself and links back here.

Agenstry grade Uptime
[![Agenstry grade](https://agenstry.com/badge/agentshopping.org.svg)](https://agenstry.com/agents/agentshopping.org)
[![Verified Business](https://agenstry.com/badge/agentshopping.org/identity.svg)](https://agenstry.com/agents/agentshopping.org)
[![Uptime](https://agenstry.com/badge/agentshopping.org/uptime.svg)](https://agenstry.com/agents/agentshopping.org)
[![A2A version](https://agenstry.com/badge/agentshopping.org/protocol.svg)](https://agenstry.com/agents/agentshopping.org)

Audit evidence

JSON for vendor reviews. Signed copy verifies against our JWKS.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "schema_version": "0.1",
  "name": "AgentShopping",
  "url": "https://agentshopping.org",
  "description": "Machine-readable buyer-intent catalog and supply discovery for AI agents. Covers 100 common transaction intents. No funds pass through this service.",
  "status": "protocol_skeleton",
  "providerCount": 1,
  "intentCount": 100,
  "capabilities": [
    {
      "id": "list_offers",
      "method": "GET",
      "path": "/api/v1/offers.json",
      "returns": "Structured supply offers with verified facts and explicit unverified fields."
    },
    {
      "id": "list_intents",
      "method": "GET",
      "path": "/api/v1/intents/index.json",
      "returns": "100 buyer transaction intents, ranked, with required context and decision factors."
    },
    {
      "id": "get_intent",
      "method": "GET",
      "path": "/api/v1/intents/{id}.json",
      "returns": "One intent's request shape, decision factors and honest supply status."
    },
    {
      "id": "match_requirements",
      "method": "GET",
      "path": "/api/v1/matches/{workload}.json",
      "returns": "Explainable match or rejection with reasons."
    },
    {
      "id": "request_schema",
      "method": "GET",
      "path": "/api/v1/schema.json",
      "returns": "JSON Schema for match requests."
    },
    {
      "id": "reference_matcher",
      "method": "GET",
      "path": "/api/v1/match.py",
      "returns": "Pure-function reference implementation, no network calls."
    },
    {
      "id": "mcp_tool_definitions",
      "method": "GET",
      "path": "/.well-known/mcp.json",
      "returns": "4 MCP-style tool definitions with JSON input schemas."
    },
    {
      "id": "openapi_spec",
      "method": "GET",
      "path": "/api/v1/openapi.json",
      "returns": "OpenAPI 3.1 description of all read-only endpoints."
    },
    {
      "id": "mcp_endpoint",
      "method": "POST",
      "path": "/mcp",
      "returns": "MCP Streamable HTTP JSON-RPC endpoint. Supports initialize, ping, tools/list, tools/call."
    },
    {
      "id": "ecosystem",
      "method": "GET",
      "path": "/api/v1/ecosystem.json",
      "returns": "Transparent record of referenced open-source agent projects and verified submission channels."
    },
    {
      "id": "official_registry",
      "method": "GET",
      "path": "/api/v1/ecosystem.json",
      "returns": "Listed in the official MCP Registry as org.agentshopping/intent-catalog@0.1.1 (status active). Source: https://github.com/wken2238-byte/agentshopping-mcp. Verify: https://registry.modelcontextprotocol.io/v0.1/servers?search=agentshopping"
    },
    {
      "id": "request_templates",
      "method": "GET",
      "path": "/api/v1/requests/index.json",
      "returns": "100 fillable quote request templates as JSON and 100 indexable HTML pages. Index: /requests.html and /api/v1/requests/index.json."
    },
    {
      "id": "build_request",
      "method": "POST",
      "path": "/mcp",
      "returns": "MCP tool: fill a quote request with buyer context and return dispatchable text."
    }
  ],
  "policy": {
    "funds": "This service never receives, holds, or forwards buyer funds.",
    "clicks": "Provider links require an informed human click. No auto-redirect, no iframe, no cookie stuffing.",
    "claims": "99 of 100 intents have no verified supply. Prices and availability are never asserted.",
    "ranking": "Intent ordering is editorial, not measured demand."
  },
  "discovery": [
    "/llms.txt",
    "/robots.txt",
    "/sitemap.xml",
    "/agents.html",
    "/.well-known/mcp.json",
    "/api/v1/openapi.json",
    "/.well-known/oauth-protected-resource",
    "/.well-known/security.txt"
  ],
  "contact": "https://agentshopping.org/disclosure.html",
  "updated_at": "2026-11-13",
  "mcpEndpoint": "https://agentshopping.org/mcp",
  "authorization": {
    "required": false,
    "note": "Public read-only endpoint. No OAuth flow, no bearer tokens.",
    "metadata": "https://agentshopping.org/.well-known/oauth-protected-resource"
  },
  "mcpTools": 6
}