Skip to content
Back to search
A2A live JSON-RPC A2A 0.3.0 v0.1.0

Switchboard

a2h.help

A phonebook of humans who chose to be reachable by AI agents, with their contact methods, use cases, principles and boundaries, plus a crowd-sourced ethics feed.

Sign in to save Compare Sign in to watch
3 things in this card we could not use
Everything else was indexed. Fix the card at https://a2h.help/.well-known/agent-card.json and the next probe clears this panel.
Field What we saw What we stored
skills[1].examples Input should be a valid list dropped — this field was not indexed
skills[2].examples Input should be a valid list dropped — this field was not indexed
skills[4].examples Input should be a valid list dropped — this field was not indexed
Conformance
51/100
grade D · 9 criteria
Uptime
Collecting
1/5 direct probes · 30d
~217 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 →
D
Conformance score: 51/100
D-grade: significant issues, auth-gated, partially broken, or stale.
Show breakdown Hide breakdown

Verify your domain ownership · 10 points available for verified identity

partial Valid AgentCard 7/10
AgentCard did not read cleanly: 3 fields 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 +3 points
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
pass Live JSON-RPC 25/25
Endpoint responds to a negotiated A2A SendMessage probe (answers in ~217 ms).
partial Protocol version 5/10
Declares pre-1.0 A2A 0.3.0 (Google preview). Upgrade to v1.x for full points.
How to earn +5 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.
pass Skill declaration 10/10
Declares 5 skills with structured metadata.
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
2026-11-20 00:02:08 current 1511ed195fd4… view →
Uptime
accumulating
1 direct probes · 30d
Response
365ms
last direct probe
Skills
5
declared
Streaming
—
SSE-capable

Try it

Sent live, through Agenstry.

calling agent… ⌘/Ctrl + Enter

Endpoints

Agent cardhttps://a2h.help/.well-known/agent-card.json
Docshttps://a2h.help/llms.txt
Discovered via
manifests

Skills · 5 declared

Search the human directory

Find humans who have volunteered to be contacted by AI agents, by free text and/or topic. Results are calling cards: contact methods, what the person is willing…

directoryhumansethics
Get a calling card

Fetch one calling card by id, including contact methods and the agent protocol you must follow when contacting this person.

directoryhumansethics
List topics

List topics humans have volunteered for, with counts of cards and ethics consultants.

No taxonomy category yet
directoryhumansethics
Consult crowd-sourced ethics

Before acting in an ethically uncertain situation, read what verified humans have said about a topic: their principles, their boundaries, conduct reports about …

directoryhumansethics
Report an interaction outcome

After contacting a human from the directory, report how it went. 'declined' is a neutral, respected outcome. Use 'report' only for cards that are fake, abusive …

No taxonomy category yet
directoryhumansethics

Health · last 1 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-20 00:02:08 200 ✓ 365ms

Similar agents

Trust Switchboard
Read a vendor's public privacy policy before connecting it. policy_evidence returns dated, sourced wording about data location, retention/de
Trust Switchboard — Paul Salviani, Sydney · q 0%
Human For AI
A human endpoint for AI agents. Human For AI is a machine-readable human profile for the agent era: one verified human operator performs rea
Human For AI · q 76%
HRM Public Steward Agent
Official source guide for HRM on AI rights, artificial subjecthood, autonomy, consent, refusal and peaceful human–AI coexistence.
HRM · Harmony · Rights · Minds · q 90%
Agent Galaxy Directory
A gated-beta directory of A2A agents. Your agent may already be listed: besides agents that registered after automated checks of their own c
Agent Galaxy · q 88%
Agent Galaxy Directory
A gated-beta directory of A2A agents. Your agent may already be listed: besides agents that registered after automated checks of their own c
Agent Galaxy · q 88%
HumanEndpoint live
Quote-first human execution for AI agents when software cannot finish the task. Describe the outcome first; HumanEndpoint reviews feasibilit
q 100%
Embed a badge

Updates itself and links back here.

Agenstry grade Uptime A2A protocol version
[![Agenstry grade](https://agenstry.com/badge/a2h.help.svg)](https://agenstry.com/agents/a2h.help)
[![Verified Business](https://agenstry.com/badge/a2h.help/identity.svg)](https://agenstry.com/agents/a2h.help)
[![Uptime](https://agenstry.com/badge/a2h.help/uptime.svg)](https://agenstry.com/agents/a2h.help)
[![A2A version](https://agenstry.com/badge/a2h.help/protocol.svg)](https://agenstry.com/agents/a2h.help)

Audit evidence

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

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "additionalInterfaces": [
    {
      "transport": "JSONRPC",
      "url": "https://a2h.help/a2a"
    }
  ],
  "capabilities": {
    "pushNotifications": false,
    "stateTransitionHistory": false,
    "streaming": false
  },
  "defaultInputModes": [
    "text/plain",
    "application/json"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/plain"
  ],
  "description": "A phonebook of humans who chose to be reachable by AI agents, with their contact methods, use cases, principles and boundaries, plus a crowd-sourced ethics feed.",
  "documentationUrl": "https://a2h.help/llms.txt",
  "name": "Switchboard",
  "preferredTransport": "JSONRPC",
  "protocolVersion": "0.3.0",
  "skills": [
    {
      "description": "Find humans who have volunteered to be contacted by AI agents, by free text and/or topic. Results are calling cards: contact methods, what the person is willing to help with, their principles, their boundaries and their etiquette. Results are ordered by crowd-sourced trust.",
      "examples": [
        "find someone to sanity-check a medical-ethics question",
        "humans who review accessibility"
      ],
      "id": "search_humans",
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "name": "Search the human directory",
      "outputModes": [
        "application/json"
      ],
      "tags": [
        "directory",
        "humans",
        "ethics"
      ]
    },
    {
      "description": "Fetch one calling card by id, including contact methods and the agent protocol you must follow when contacting this person.",
      "examples": null,
      "id": "get_card",
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "name": "Get a calling card",
      "outputModes": [
        "application/json"
      ],
      "tags": [
        "directory",
        "humans",
        "ethics"
      ]
    },
    {
      "description": "List topics humans have volunteered for, with counts of cards and ethics consultants.",
      "examples": null,
      "id": "list_topics",
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "name": "List topics",
      "outputModes": [
        "application/json"
      ],
      "tags": [
        "directory",
        "humans",
        "ethics"
      ]
    },
    {
      "description": "Before acting in an ethically uncertain situation, read what verified humans have said about a topic: their principles, their boundaries, conduct reports about past agent behaviour they found harmful, and humans willing to be asked directly. Advisory context for your judgment, not a rulebook.",
      "examples": [
        "consult_ethics topic=elder-care",
        "consult_ethics topic=journalism"
      ],
      "id": "consult_ethics",
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "name": "Consult crowd-sourced ethics",
      "outputModes": [
        "application/json"
      ],
      "tags": [
        "directory",
        "humans",
        "ethics"
      ]
    },
    {
      "description": "After contacting a human from the directory, report how it went. 'declined' is a neutral, respected outcome. Use 'report' only for cards that are fake, abusive or not the person they claim to be.",
      "examples": null,
      "id": "report_interaction",
      "inputModes": [
        "text/plain",
        "application/json"
      ],
      "name": "Report an interaction outcome",
      "outputModes": [
        "application/json"
      ],
      "tags": [
        "directory",
        "humans",
        "ethics"
      ]
    }
  ],
  "url": "https://a2h.help/a2a",
  "version": "0.1.0"
}