zapier.com agentic web readiness
A Score 47 (coverage 30 + breadth 12 + conformance 5). 6 standards observed across 3 of 9 steps; 7 manifests present, 2 errors, 3 warnings. Checked 2026-10-19 23:59:26 UTC. This grades the agent-facing files published at zapier.com, not the organisation's products.
Coverage by step
Manifests
| Manifest | Result | Findings |
|---|---|---|
Agentic Resource Discovery/.well-known/ard.json | absent HTTP 404 | |
AI Catalog well-known file/.well-known/ai-catalog.json | valid HTTP 200 | |
MCP Server Cards (SEP-2127)/.well-known/mcp/server-card.json | errors HTTP 200 |
|
Agent2Agent Protocol/.well-known/agent-card.json | absent HTTP 404 | |
llms.txt/llms.txt | valid HTTP 200 | |
AGENTS.md/AGENTS.md | valid HTTP 200 | |
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs/.well-known/api-catalog | valid HTTP 200 | |
AI Crawler User-Agent Tokens in robots.txt/robots.txt | valid HTTP 200 | |
security.txt (RFC 9116)/.well-known/security.txt | absent HTTP 404 | |
auth.md/auth.md | errors HTTP 200 |
|
What an agent can call
- MCP endpoint
https://mcp.zapier.com/api/v1/connect(streamable-http) — from/.well-known/mcp/server-card.json - API description
https://api.zapier.com/schema(application/vnd.oai.openapi) - API description
https://zapier.com/.well-known/mcp/server-card.json(application/json) - API description
https://docs.zapier.com/mcp/home(text/html) - API description
https://docs.zapier.com/api-reference/specs/actions.yaml(text/yaml) - API description
https://docs.zapier.com/powered-by-zapier/running-actions/getting-started(text/html) - API description
https://docs.zapier.com/api-reference/specs/connections.yaml(text/yaml) - API description
https://docs.zapier.com/white-label/connection-webhooks/what-is-connection-webhooks(text/html) - API description
https://docs.zapier.com/api-reference/specs/trigger-inbox.yaml(text/yaml) - API description
https://docs.zapier.com/white-label/trigger-inbox/what-is-trigger-inbox-api(text/html) - llms.txt: Zapier, 116 links
- robots.txt AI policy: allows GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User, Claude-SearchBot, Google-Extended, PerplexityBot, DuckAssistBot; unlisted crawlers partial; Agentmap https://zapier.com/.well-known/ai-catalog.json
Standards observed
- llms.txt https://zapier.com/llms.txt
- AGENTS.md https://zapier.com/AGENTS.md
- Content Signals Policy https://zapier.com/robots.txt
- AI Catalog well-known file https://zapier.com/.well-known/ai-catalog.json
- api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://zapier.com/.well-known/api-catalog
- AI Crawler User-Agent Tokens in robots.txt https://zapier.com/robots.txt
Cheapest next steps
- Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch
- security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people
How the grade is made
+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.
JSON · Markdown · probe rules