Zapier serves an AI Catalog
manifest at /.well-known/ai-catalog.json on zapier.com, declaring
13 agentic resources
that a discovery service can index without asking anyone’s permission.
Correctly shaped — every hard check passes — but optional affordances are missing.
ARD conformance tool v0.5.0
PASS
Run against this exact body with the project’s own
conformance CLI.
Declared spec version
1.0
The specVersion in the manifest. AI Catalog 1.0 is current; anything lower is an earlier draft.
Optional affordances missing. None of these break a client, but each one costs the publisher search relevance or verifiability.
host-identifier-not-did-web
13 entries
6 media types
29 representative queries
0 trust manifests
Host identifier: zapier.com
What this manifest advertises
Zapier MCP
urn:air:zapier.com:mcp
Connect any MCP-aware agent to 9,000+ app integrations and 40,000+ actions. Remote streamable-HTTP server with OAuth2. Take actions across Slack, Gmail, Google Sheets, Jira, GitHub, HubSpot, and thousands more.
WebMCP manifest exposing machine-discoverable website tools for browser-resident agents, such as browsing Zapier's app directory and docs before navigating.
OpenAPI 3.1 spec for the Partner API. Programmatically manage connections, Zaps, and embedded workflows for Powered by Zapier and White Label integrations.
Unified reference for the public Zapier APIs on api.zapier.com — build workflows, execute actions, set up trigger inboxes, and more. Browsable by developers and AI agents, rendered from per-service OpenAPI specs.
Front-door router. Picks the right surface (MCP for AI clients, SDK for code, CLI for terminal) for connecting Zapier to an agent, with steps for each.
Canonical agent-readable map of Zapier. Per-surface indexes and topic-keyed cross-references with stable anchors. Expanded inline content at /llms-full.txt.
The canonical list of the 9,000+ apps Zapier connects to. Use to check whether Zapier supports a given app or what actions it exposes. Per-app pages at zapier.com/apps/{slug}/integrations.
The publishing guide asks for three things at the transport layer, because a crawler is the
consumer that matters and a crawler is a browser-shaped client.
HTTPS only — yes (HTTP 200)
Content-Type: application/json —
yes
Access-Control-Allow-Origin: * —
yes
Evidence. Fetched https://zapier.com/.well-known/ai-catalog.json on 2026-07-31, HTTP
200. The verbatim body is stored alongside its manifest in the
Zapier repository
as ai-catalog/zapier-ai-catalog.json. Nothing on this page is derived
or generated: an AI Catalog manifest is served from the publisher’s own domain or it does not
exist, which makes it — like an
A2A Agent Card — one of the few agent artifacts that cannot be
produced on a provider’s behalf. Grades are recomputed on every build; the specification is a
v0.9 draft and
these verdicts will move when it does.
Every descriptor here is available over the APIs.io API and to AI agents over MCP. Agent Discovery is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for agent discovery
3 MCP tools reach this
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.