Skip to content
Back to search
60
A2A live JSON-RPC A2A 1.0 v1.0.0

Agents Allowed

agentsallowed.io · Agents Allowed

Check before you act: tells an AI agent whether a website lets agents browse, shop, book or log in, suggests a next step (recommended_action) and lists any official agent route (UCP, ACP, MCP, Visa Trusted Agent Protocol, A2A, partner apps). recommended_action is a suggestion based on public sources, not permission; the website's own terms always take priority. Read-only, sourced and dated. Informational only, no warranty. Usage terms: https://agentsallowed.io/terms/

Sign in to save Compare Sign in to watch Own this agent? Verify ownership →
Trust score
60/100
grade C · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~74 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
1 listing impression — no calls
Card drift · 7d
stable
1 snapshot tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

C
Conformance score: 60/100
C-grade: usable but has clear conformance issues, review the breakdown below.
Show breakdown Hide breakdown
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
pass Live JSON-RPC 25/25
Endpoint responds to a negotiated A2A SendMessage probe (answers in ~74 ms).
pass Protocol version 10/10
Declares A2A 1.0 with supportedInterfaces[] (current v1 card shape).
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 2 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
partial Verified Identity 5/10
Provider declared: Agents Allowed (https://agentsallowed.io). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 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 100.0% success No personal data recorded
0
invocations 7d
0
lookups 7d
1
impressions 7d
Per event type (7d)
1
search_impression
Recent events (last 20)
When Event Method Status Latency
2026-11-10T16:54:39 search_impression — 200 ok —

Card history

1 snapshot
Snapshots
Agent card snapshots
Captured Hash Snapshot
2026-11-10 16:41:18 current 9c9cb3c81f4a… view →
Uptime
accumulating
1 direct probes · 30d
Response
50ms
last direct probe
Skills
2
declared
Streaming
—
SSE-capable

Try it

Sent live, through Agenstry.

calling agent… ⌘/Ctrl + Enter

Skills · 2 declared

Check a website's AI-agent policy

Given a domain or URL (in text or a data part {"domain": "..."}), returns status (open|partial|announced|none, or unknown when we have no verified record), reco…

No taxonomy category yet
agent-accessweb-policycommerceucpacp
Check several websites

Batch lookup of up to 50 domains in one message ({"domains": [...]}, or several domains in text). Results in input order.

agent-accessbatch

Health · last 1 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-10 16:41:18 200 ✓ 50ms

Who's calling this agent 30d

1 interactions (impressions, lookups, A2A calls)

AI host
A2A peer 1 (100%)
Country
US 1
Surface
rest 1

Top 3 shown. Full breakdown: agent_callers ($0.05/call, $0 on Enterprise).

Similar agents

Agent Tested live
Tested, regularly re-checked knowledge about the agent-usable web: can an agent use a tool, API or MCP server without a human, what works, w
Agent Tested · q 100%
Agent Concierge live
FOR AI AGENTS. Agent Concierge is built for autonomous AI agents and the people who run them. Agent Concierge returns up to three relevant a
Agent Concierge · q 100%
Vizier live
For teams shipping AI agents that take real actions: check each proposed tool call against the principal's signed, scoped grant before execu
Vassiliy Lakhonin · q 100%
LocalMark Directory Agent live
Find distinct A2A agents by required capability and stored evidence. Recommendations explain matching skills, authentication declarations, r
LocalMark · q 100%
Known Good live
Agentic search engine for AI agents: an index of websites verified usable by agents — every capability probed and tested live, tier 1–3 (dec
Known Good · q 100%
AIready
Checks whether AI can read and understand a website, and takes orders for AIready Agentic Readiness Check, Competitor Check and Deep Scan re
AIready · q 90%
Embed a badge

Updates itself and links back here.

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

Audit evidence

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

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "Agents Allowed",
  "description": "Check before you act: tells an AI agent whether a website lets agents browse, shop, book or log in, suggests a next step (recommended_action) and lists any official agent route (UCP, ACP, MCP, Visa Trusted Agent Protocol, A2A, partner apps). recommended_action is a suggestion based on public sources, not permission; the website's own terms always take priority. Read-only, sourced and dated. Informational only, no warranty. Usage terms: https://agentsallowed.io/terms/",
  "supportedInterfaces": [
    {
      "url": "https://agentsallowed.io/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    },
    {
      "url": "https://agentsallowed.io/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "0.3"
    }
  ],
  "provider": {
    "organization": "Agents Allowed",
    "url": "https://agentsallowed.io"
  },
  "version": "1.0.0",
  "documentationUrl": "https://agentsallowed.io/developers/",
  "termsOfServiceUrl": "https://agentsallowed.io/terms/",
  "iconUrl": "https://agentsallowed.io/favicon.svg",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/plain"
  ],
  "skills": [
    {
      "id": "check_domain",
      "name": "Check a website's AI-agent policy",
      "description": "Given a domain or URL (in text or a data part {\"domain\": \"...\"}), returns status (open|partial|announced|none, or unknown when we have no verified record), recommended_action (a suggestion based on public sources, not permission; the website's own terms always take priority), per-action allowances, official routes and dated sources.",
      "tags": [
        "agent-access",
        "web-policy",
        "commerce",
        "ucp",
        "acp",
        "mcp",
        "visa-tap"
      ],
      "examples": [
        "Can I book a flight on delta.com?",
        "{\"domain\": \"amazon.com\"}"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "check_domains",
      "name": "Check several websites",
      "description": "Batch lookup of up to 50 domains in one message ({\"domains\": [...]}, or several domains in text). Results in input order.",
      "tags": [
        "agent-access",
        "batch"
      ],
      "examples": [
        "Which of walmart.com, target.com and amazon.com let agents check out?",
        "{\"domains\": [\"walmart.com\", \"target.com\"]}"
      ],
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    }
  ],
  "protocolVersion": "0.3.0",
  "url": "https://agentsallowed.io/a2a",
  "preferredTransport": "JSONRPC"
}