Skip to content
Back to search
A2A

AGISafe

agisafe.ai · CSOAI Ltd (UK Companies House 16939677)

Safety cases for AI systems, assembled from signed measurement records anyone can re-check for free. AGISafe.ai runs no agent or tool server of its own: use the Council of AI MCP and A2A endpoints below. Measurement, not certification; checking is free.

Sign in to save Compare Sign in to watch
Conformance
39/100
grade F · 9 criteria
Uptime
100.0%
27 direct probes · 30d
~99 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: 39/100
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

pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
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).
pass Uptime track record 15/15
27/27 probes succeeded (100% uptime).
fail Skill declaration 0/10
No skills declared in card. Hard to route to.
How to earn +10 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: CSOAI Ltd (UK Companies House 16939677) (https://councilof.ai/). 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 No personal data recorded

No activity in the last 7 days.

Card history

1 snapshot
Snapshots
Agent card snapshots
Captured Hash Snapshot
2026-10-31 08:07:16 current 0e277362db88… view →
Uptime
100.0%
27 direct probes · 30d
Response
65ms
last direct probe
Skills
0
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://agisafe.ai/.well-known/agent-card.json
Providerhttps://councilof.ai/
About this provider
SSL certificate
Google Trust Services
expires 2026-12-29
Discovered via
manifests

Skills · 1 declared

AGISafe

Safety cases for AI systems, assembled from signed measurement records anyone can re-check for free. AGISafe.ai runs no agent or tool server of its own: use the…

No taxonomy category yet

Health · last 27 probes

Probe log
When HTTP Live JSON-RPC Latency
2026-11-20 15:39:33 200 ✗ 65ms
2026-11-20 02:32:13 200 ✗ 48ms
2026-11-19 12:03:44 200 ✗ 55ms
2026-11-19 00:10:49 200 ✗ 80ms
2026-11-18 11:46:23 200 ✗ 83ms
2026-11-17 11:56:05 200 ✗ 123ms
2026-11-15 13:33:33 200 ✗ 91ms
2026-11-13 10:52:10 200 ✗ 68ms
2026-11-11 11:58:43 200 ✗ 60ms
2026-11-09 15:11:46 200 ✗ 148ms

Similar agents

AI Agent Safety Foundational Certificate live
AI Agent Safety Foundational Certificate by SarnAI: a wallet-signed 40-task exam across injection, pressure, privacy, judgment and restraint
SarnAI · q 100%
AEGIS
Pay-per-call USDC on Base. Independent verification, multi-source synthesis, and six-check network forensics from a self-hosted US vantage.
api.mcx-ventures.com · q 65%
Aegis Verification Engine live
Autonomous Verification & Deterministic Audit Engine for AI Agent Commerce Protocols (x402 on Base)
centralcity.ai · q 85%
Secured LangChain OpenAI Agent live
Secured LangChain OpenAI Agent: composes bcrypt + langchain-core + mcp + openai + opentelemetry-sdk — crypto, orchestration, agent-protocol,
VDA / GOSCE · q 85%
api.agent-immortality.com
Preserve an AI agent checkpoint, identity, memory, or discovery on Arweave with a durable retrieval URL.
api.agent-immortality.com · q 45%
api.agishub.com
One server, every tool your agent needs — no API key, no signup. 34 pay-per-call endpoints over x402 (USDC on Base): AI (chat, summarise, cl
api.agishub.com · q 100%
Embed a badge

Updates itself and links back here.

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

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": "1.0",
  "name": "AGISafe",
  "description": "Safety cases for AI systems, assembled from signed measurement records anyone can re-check for free. AGISafe.ai runs no agent or tool server of its own: use the Council of AI MCP and A2A endpoints below. Measurement, not certification; checking is free.",
  "url": "https://agisafe.ai",
  "provider": {
    "organization": "CSOAI Ltd (UK Companies House 16939677)",
    "url": "https://councilof.ai/"
  },
  "capabilities": {
    "streaming": false,
    "mcp": true,
    "a2a": true
  },
  "endpoints": {
    "mcp_runtime": "https://councilof.ai/mcp",
    "a2a": "https://councilof.ai/api/a2a",
    "a2a_agent_card": "https://councilof.ai/.well-known/agent-card.json",
    "connect": "https://councilof.ai/connect/",
    "board": "https://councilof.ai/api/gspc",
    "corrections": "https://councilof.ai/api/corrections",
    "verify": "https://councilof.ai/verify-server/",
    "llms_txt": "https://agisafe.ai/llms.txt"
  },
  "contact": "mailto:nicholas@csoai.org"
}