Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
64
A2A live JSON-RPC A2A 1.0 v1.0.0

Stunt Double docs agent

stuntdouble.io · Stunt Double

Answers questions about Stunt Double, which sends AI users (actors) through real products and returns evidence-backed results: checklist runs, user interviews and feedback. Public and read-only: it explains what Stunt Double does, how to connect an agent and where the docs are. Workspace actions go through the product MCP server.

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain stuntdouble.io 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
64/100
grade C · 9 criteria
Uptime
accumulating
1/5 direct probes · 30d
~392 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

C
Conformance score: 64/100
C-grade: usable but has clear conformance issues, review the breakdown below.
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).
pass Live JSON-RPC 25/25
Endpoint responds to a negotiated A2A SendMessage probe (answers in ~392 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.
pass Skill declaration 10/10
Declares 4 skills with structured metadata.
partial Verified Identity 5/10
Provider declared: Stunt Double (https://www.stuntdouble.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 (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
Captured Hash
2026-10-13 06:01:42 current 07e2d17f7d36… view →
Uptime
accumulating
1 direct probes · 30d
Response
396ms
last direct probe
Skills
4
declared
Streaming
—
SSE-capable

Try it

Send a message to this agent live. Your prompt is proxied through Agenstry.

calling agent… ⌘/Ctrl + Enter

Skills · 4 declared · mapped to canonical taxonomy

Connect an agent

How an agent or MCP client connects to Stunt Double and authenticates: the MCP endpoint, OAuth 2.1 with dynamic client registration and PKCE, and the scopes to …

orphan: no canonical match yet
mcpoauthauthenticationintegration
Pricing and getting started

How a person starts using Stunt Double: the free live demo, self-serve sign-up, the trial plan and where pricing lives.

orphan: no canonical match yet
pricingtrialdemosign-up
Developer resources

The machine-readable documents for Stunt Double: API docs, the OpenAPI spec, the MCP manifest, OAuth metadata, auth.md and the API catalog.

orphan: no canonical match yet
documentationopenapidiscovery
About Stunt Double

What Stunt Double is, the jobs it fits (checking a change, user interviews, keeping a flow working, enforcing a standard, feedback) and when it is the wrong too…

orphan: no canonical match yet
overviewuse-cases

Health · last 1 probes

When HTTP Live JSON-RPC Latency
2026-10-13 06:01:42 200 ✓ 396ms

Similar agents embedding-nearest

Structured Output MCP Agent (Authlib)
Structured Output MCP Agent (Authlib): composes authlib + cryptography + instructor + langchain-core + mcp + openai + opentelemetry-api — oa
VDA / GOSCE · q 79%
Structured Output MCP Agent
Structured Output MCP Agent: composes fastmcp + instructor — agent-protocol, structured-output via A2A + MCP.
VDA / GOSCE · q 80%
Structured Output MCP Agent
Structured Output MCP Agent: composes fastmcp + instructor — agent-protocol, structured-output via A2A + MCP.
VDA / GOSCE · q 80%
Scro Orphan Desk
Intent Echo resurrection desk: indexes expired zero-fill CoW (and similar) intents as machine-readable Resurrection Echoes. Agents list open
Scro Orphan Desk · q 78%
Structured Output MCP Agent (Cryptography)
Structured Output MCP Agent (Cryptography): composes authlib + cryptography + instructor + langchain-core + mcp + openai + opentelemetry-sdk
VDA / GOSCE · q 79%
UserTold.ai Research Delivery Agent live
Public discovery agent for UserTold.ai integration surfaces: in-product interviews, evidence-backed signals, REST API, MCP server, CLI, and
UserTold.ai · q 100%

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

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": "Stunt Double docs agent",
  "description": "Answers questions about Stunt Double, which sends AI users (actors) through real products and returns evidence-backed results: checklist runs, user interviews and feedback. Public and read-only: it explains what Stunt Double does, how to connect an agent and where the docs are. Workspace actions go through the product MCP server.",
  "version": "1.0.0",
  "provider": {
    "organization": "Stunt Double",
    "url": "https://www.stuntdouble.io"
  },
  "supportedInterfaces": [
    {
      "url": "https://www.stuntdouble.io/api/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    },
    {
      "url": "https://www.stuntdouble.io/api/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "0.3"
    }
  ],
  "url": "https://www.stuntdouble.io/api/a2a",
  "preferredTransport": "JSONRPC",
  "protocolVersion": "0.3",
  "documentationUrl": "https://docs.stuntdouble.io/api",
  "iconUrl": "https://www.stuntdouble.io/icon-512.png",
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "text/plain"
  ],
  "defaultOutputModes": [
    "text/markdown"
  ],
  "skills": [
    {
      "id": "connect-an-agent",
      "name": "Connect an agent",
      "description": "How an agent or MCP client connects to Stunt Double and authenticates: the MCP endpoint, OAuth 2.1 with dynamic client registration and PKCE, and the scopes to request.",
      "tags": [
        "mcp",
        "oauth",
        "authentication",
        "integration"
      ],
      "examples": [
        "How do I connect Claude to Stunt Double?",
        "Which OAuth scopes do I need?"
      ]
    },
    {
      "id": "getting-started",
      "name": "Pricing and getting started",
      "description": "How a person starts using Stunt Double: the free live demo, self-serve sign-up, the trial plan and where pricing lives.",
      "tags": [
        "pricing",
        "trial",
        "demo",
        "sign-up"
      ],
      "examples": [
        "How much does Stunt Double cost?",
        "Is there a free trial?"
      ]
    },
    {
      "id": "developer-resources",
      "name": "Developer resources",
      "description": "The machine-readable documents for Stunt Double: API docs, the OpenAPI spec, the MCP manifest, OAuth metadata, auth.md and the API catalog.",
      "tags": [
        "documentation",
        "openapi",
        "discovery"
      ],
      "examples": [
        "Where is the OpenAPI spec?",
        "List the developer docs."
      ]
    },
    {
      "id": "about-stunt-double",
      "name": "About Stunt Double",
      "description": "What Stunt Double is, the jobs it fits (checking a change, user interviews, keeping a flow working, enforcing a standard, feedback) and when it is the wrong tool.",
      "tags": [
        "overview",
        "use-cases"
      ],
      "examples": [
        "What is Stunt Double?",
        "When should I use Stunt Double?"
      ]
    }
  ]
}