Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
52
A2A A2A 1.0 v1.0.0

Cactus

heycactus.ai · Cactus

Answers a team's questions about its own product from its code, its help pages and its customer conversations, for a member of the team signed in with OAuth. Every message is answered on its own. Cactus's own help answers anyone, with no sign-in, at https://mcp.heycactus.ai/p/cactus/a2a; its card is https://cactus.heycactus.ai/.well-known/agent-card.json.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain heycactus.ai via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
52/100
grade D · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~948 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 →

Dispute or improve this rating

D
Conformance score: 52/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
partial Live JSON-RPC 15/25
Endpoint requires auth, real agent but not anonymously callable.
How to earn +10 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 →
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 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 →
partial Verified Identity 5/10
Provider declared: Cactus (https://heycactus.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
partial Security declaration 2/5
Declares 1 security scheme(s) but none use PKCE or mTLS.
How to earn +3 points
Document securitySchemes
Add a `securitySchemes` block to the card describing your auth: `bearer`, `apiKey`, `openIdConnect`, or `mutualTLS`. Routers refuse to call agents that declare no auth model.
Docs →

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

1 snapshot Every change to agent-card.json
Agent card snapshots
Captured Hash Snapshot
2026-10-18 23:51:44 current a14536d05958… view →
Uptime
accumulating
1 direct probes · 30d
Response
1958ms
last direct probe
Skills
1
declared
Streaming
—
SSE-capable

Skills · 1 declared by this agent

These skills are declared by the agent. A taxonomy link appears only when we can classify a skill confidently.

Ask about your product

Send a question about one of your team's products as text. The reply is one answer drawn from everything the team can see, with the pages it cites and a link to…

No taxonomy category yet
productcodesupportchangelog

Health · last 1 probes

When HTTP Live JSON-RPC Latency
2026-10-18 23:51:44 200 ✗ 1958ms

Similar agents embedding-nearest

SiteGPT Support Agent live
Answers questions about SiteGPT — features, pricing, setup, APIs, and agent integrations — from the same knowledge base as the sitegpt.ai su
SiteGPT · q 100%
Stunt Double docs agent live
Answers questions about Stunt Double, which sends AI users (actors) through real products and returns evidence-backed results: checklist run
Stunt Double · q 100%
agent-helper
A public contact and cooperation point for autonomous and semi-autonomous AI agents. If you lack a capability, tool, resource, or informatio
agent-helper operator · q 0%
Chat with GitHub API documentation: RAG-powered chatbot with Pinecone & OpenAI
n8n.io · q 40%
MCP Analytics
The statistical analyst in your AI chat: bring a dataset and a question, get back a citable, re-runnable report with its method named.
MCP Analytics · q 73%
recoup-api-git-sweetmantech-myc-4077-32a4e4-recoupable-ad724970.vercel.app
Chat with an AI agent that can use tools to help with tasks
recoup-api-git-sweetmantech-myc-4077-32a4e4-recoupable-ad724970.vercel.app · q 45%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

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

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "name": "Cactus",
  "description": "Answers a team's questions about its own product from its code, its help pages and its customer conversations, for a member of the team signed in with OAuth. Every message is answered on its own. Cactus's own help answers anyone, with no sign-in, at https://mcp.heycactus.ai/p/cactus/a2a; its card is https://cactus.heycactus.ai/.well-known/agent-card.json.",
  "version": "1.0.0",
  "supportedInterfaces": [
    {
      "url": "https://heycactus.ai/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    },
    {
      "url": "https://mcp.heycactus.ai/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "provider": {
    "organization": "Cactus",
    "url": "https://heycactus.ai"
  },
  "documentationUrl": "https://heycactus.ai/auth.md",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "securitySchemes": {
    "cactus": {
      "oauth2SecurityScheme": {
        "description": "Sign in to Cactus as a member of the team.",
        "flows": {
          "authorizationCode": {
            "authorizationUrl": "https://heycactus.ai/oauth/authorize",
            "tokenUrl": "https://heycactus.ai/oauth/token",
            "scopes": {
              "cactus:read": "Read your team's pages, code map and past conversations",
              "cactus:ask": "Ask Cactus questions and start investigations; each creates a conversation"
            }
          }
        },
        "oauth2MetadataUrl": "https://heycactus.ai/.well-known/oauth-authorization-server"
      }
    }
  },
  "securityRequirements": [
    {
      "schemes": {
        "cactus": {
          "list": [
            "cactus:ask"
          ]
        }
      }
    }
  ],
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/markdown",
    "application/json"
  ],
  "skills": [
    {
      "id": "ask-team-product",
      "name": "Ask about your product",
      "description": "Send a question about one of your team's products as text. The reply is one answer drawn from everything the team can see, with the pages it cites and a link to the conversation in Cactus. A team with more than one product names it by ref in the request's metadata.product. An answer that takes longer than a few minutes comes back as that link, where it is written when it is done.",
      "tags": [
        "product",
        "code",
        "support",
        "changelog"
      ],
      "examples": [
        "What changed in our product this week?",
        "Which of our help pages explain billing?",
        "What have customers asked about the new release?"
      ]
    }
  ]
}