AI Catalog manifest · Speakeasy

Speakeasy

Speakeasy serves an AI Catalog manifest at /.well-known/ai-catalog.json on speakeasy.com, declaring 6 agentic resources that a discovery service can index without asking anyone’s permission.

Open the live manifest → Speakeasy provider profile

Structural grade · AI Catalog 1.0

Near-Conformant

Correctly shaped — every hard check passes — but optional affordances are missing.

ARD conformance-test v0.9.1 (ards-project/ard-spec)

PASS

Run against this exact body with the project’s own conformance CLI.

Discovery path

predecessor

Answered only at /.well-known/ai-catalog.json. ARD v0.91 renamed the path to /.well-known/ard.json and made the old one an optional courtesy, so a consumer implementing only the current spec will not find this manifest.

Declared spec version

1.0

The specVersion in the manifest. 1.0 is current for the AI Catalog data model; anything lower is an earlier draft. ARD reads this field as transport-defined and ignores it.

Optional affordances missing. None of these break a client, but each one costs the publisher search relevance or verifiability.

content-type-not-ai-catalog-json
entry-no-representativeQueries
host-identifier-not-did-web

6 entries

6 media types

9 representative queries

0 trust manifests

Host identifier: speakeasy.com

What this manifest advertises

Speakeasy Platform MCP

urn:air:speakeasy.com:mcp:platform

MCP server for operating the Speakeasy AI Control Plane end to end: register and manage MCP servers, search the catalog, distribute servers and skills to teams, query MCP usage events, metrics, and traces, and search the platform docs with cited answers. OAuth 2.1 with automatic token refresh.

application/mcp-server artifact →

“Register this remote MCP server with my organization and distribute it to the engineering team”
“Why is my MCP server failing? Diagnose and repair it”
“Show MCP usage metrics and traces for the last week”

Speakeasy agent setup instructions

urn:air:speakeasy.com:setup:agents-md

Validated per-agent install commands for the Speakeasy Platform MCP server and official skills, covering Claude Code, Codex, Cursor, Windsurf, OpenCode, GitHub Copilot, Claude Desktop, and Gemini CLI.

text/markdown artifact →

Speakeasy Docs MCP

urn:air:speakeasy.com:mcp:docs-mcp

MCP server that turns Markdown documentation into a high-signal, agent-ready source. Agents search, retrieve, and cite first-party docs through standard MCP tools instead of guessing from training data or scraping HTML.

application/mcp-server-card+json artifact →

“How do I generate an MCP server from an OpenAPI spec with Speakeasy?”
“Search the Speakeasy docs for OAuth 2.1 configuration”
“What are the Speakeasy CLI commands for Terraform provider generation?”

Speakeasy Platform API

urn:air:speakeasy.com:api:platform

Machine-readable OpenAPI description of the Speakeasy API for programmatic access to the AI control plane, SDK, and MCP generation platform.

application/openapi+yaml artifact →

Speakeasy Agent Skills

urn:air:speakeasy.com:skills:speakeasy-api

Official Speakeasy skills for AI coding agents covering SDK, MCP server, Terraform provider, and CLI generation from an OpenAPI spec.

application/ai-skill+md artifact →

Speakeasy AI Control Plane

urn:air:speakeasy.com:plugin:ai-control-plane

The AI control plane for the AI-native enterprise. Connect, control, secure, and observe every AI agent (Claude, ChatGPT, Cursor, Copilot, Codex, internal agents) and the systems they reach.

application/ai-plugin+json artifact →

“How do I govern which MCP servers my team's AI agents can access?”
“How do I detect shadow AI and prompt injection across AI clients?”
“How do I add SSO and RBAC in front of an MCP server?”

How it is served

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://speakeasy.com/.well-known/ai-catalog.json on 2026-09-13, HTTP 200. The verbatim body is stored alongside its manifest in the Speakeasy repository as ai-catalog/speakeasy-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.

Work with this as data

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.

All 92 tools →

Call it yourself

curl for this page

Search the catalog

curl "https://apis.io/api/v1/search?q=speakeasy&limit=10"

Everything under a tag

curl "https://apis.io/api/v1/tags/speakeasy"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.