Weaviate serves an AI Catalog
manifest at /.well-known/ai-catalog.json on weaviate.io, declaring
10 agentic resources
that a discovery service can index without asking anyone’s permission.
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.
⚠ Hard checks failed. An ARD client cannot assume this manifest parses to the model the specification defines.
host-no-identifier
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
cors-not-readable-cross-origin
10 entries
5 media types
26 representative queries
0 trust manifests
Host identifier: none
What this manifest advertises
Weaviate resources for AI agents
urn:air:weaviate.io:guide:agents
Entry point for AI agents and coding assistants: which Weaviate resource to use for which task, how to install the official Weaviate Agent Skills, and the default recommendations for building on Weaviate.
“which Weaviate resource should an AI agent start from”
“how do I install the official Weaviate agent skills”
“what is the recommended way for a coding agent to use Weaviate”
Weaviate authentication guide
urn:air:weaviate.io:guide:auth
Machine-readable guidance for Weaviate Cloud API keys, applicable OIDC deployments, RBAC least privilege, credential rotation and revocation, Cloud onboarding, and official SDK installation.
Markdown overview of weaviate.io with links to the markdown version of each main page: quickstart, product, deployment, pricing, security, and learning resources.
Condensed product guidance for language models following the llms.txt convention: what Weaviate is, recommended server and client versions, architecture, use cases, and canonical links.
“which Weaviate client library version should I use”
“give me a condensed overview of the Weaviate stack for an LLM”
Weaviate Database Operations (Agent Skill)
urn:air:weaviate.io:skill:weaviate
Official Agent Skill for working with Weaviate collections: semantic, keyword, and hybrid search, natural-language queries with generated answers, collection creation and inspection, filtered fetching, and data import from PDF, CSV, JSON, and JSONL. Install with: npx skills add weaviate/agent-skills
“create a Weaviate collection and import a CSV file”
“ask a natural language question over data stored in Weaviate”
Weaviate Cookbooks (Agent Skill)
urn:air:weaviate.io:skill:weaviate-cookbooks
Official Agent Skill containing architectural blueprints for building AI applications on Weaviate: Query Agent chatbot, data explorer, multimodal PDF RAG, basic and advanced RAG, basic and agentic agents, plus optional frontend guidance.
“show me a reference architecture for an agentic RAG pipeline”
Weaviate REST API description
urn:air:weaviate.io:api:rest
Machine-readable description of the Weaviate REST API in Swagger 2.0 (OpenAPI 2.0) format. It covers REST endpoints only: most client read and write operations use gRPC and are not described here.
Shortest path to a working Weaviate setup: connect to Weaviate Cloud or a local instance, create a collection, insert data, and run a semantic or hybrid query.
“connect to Weaviate and run my first hybrid query”
Weaviate pricing guidance (markdown)
urn:air:weaviate.io:guide:pricing
Plan tiers, prices, and feature breakdowns for Weaviate Database and Engram, including the pricing dimensions that drive a Database bill and the per-run model that drives an Engram bill.
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: * —
no — header absent
Evidence. Fetched https://weaviate.io/.well-known/ai-catalog.json on 2026-09-13, HTTP
200. The verbatim body is stored alongside its manifest in the
Weaviate repository
as ai-catalog/weaviate-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.
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.