Airtable serves an AI Catalog
manifest at /.well-known/ai-catalog.json on airtable.com, declaring
10 agentic resources
that a discovery service can index without asking anyone’s permission.
Fails a hard check in the data model. A catalog in spirit rather than in schema.
ARD conformance tool v0.5.0
FAIL
Run against this exact body with the project’s own
conformance CLI — 1 critical error.
Declared spec version
1.0
The specVersion in the manifest. AI Catalog 1.0 is current; anything lower is an earlier draft.
⚠ Hard checks failed. An ARD client cannot assume this manifest parses to the model the specification defines.
root-collections-removed-by-adr-0003
10 entries
3 media types
29 representative queries
0 trust manifests
Host identifier: did:web:airtable.com
What this manifest advertises
Airtable MCP Server
urn:air:airtable.com:server:mcp
Official Airtable MCP server. Connects an AI client to a user's Airtable bases over OAuth so it can discover schemas and read, create, update, and delete records, fields, tables, and comments, plus query Interface pages. Supports workspace listing, base search, table schema introspection, full CRUD on records/fields/tables, record search with fuzzy matching, record comments, Interface pages for dashboards, and statistical analysis with grouping and filtering. All actions respect the user's existing permissions. SOC 2 Type II certified, HIPAA-eligible, GDPR compliant, FedRAMP authorized.
“set up a collaborative database with linked records, automations, and real-time editing”
“build a CRM to track deals, contacts, and pipeline stages”
“create a project tracker with task dependencies, owners, and status updates”
“migrate spreadsheet data into a relational database with proper field types”
“generate a summary report grouped by category from structured records”
Agent Activity Log Skill
urn:air:airtable.com:skill:agent-activity-log
Scaffold and operate an opt-in `Agent activity log` table that records what the agent did, decided, and got blocked on across a long-running or multi-session Airtable workflow. Use whenever a workflow skill (product-ops, sales-ops, marketing-ops, etc.) is being set up for an agent-driven motion (recurring triage, multi-step plan, automated monitoring, agentic workflow), or when the user explicitly asks for "agent activity tracking," "audit log of agent decisions," "agent memory," "track what the agent did," or similar. The pattern is opt-in (front-load the offer, frame as auditability for the user's benefit, not surveillance). Composes into workflow skills the same way `show-airtable-link` does — workflow skills point at this skill rather than re-implementing the schema inline.
“log all agent actions and decisions to an audit trail”
“track what an AI agent changed in my database for compliance”
Airtable CLI Skill
urn:air:airtable.com:skill:airtable-cli
Lists bases, reads and writes records, manages tables and fields, filters and searches data in Airtable via the `airtable-mcp` CLI. Use when the task involves Airtable data or the user mentions airtable-mcp, bases, tables, records, or fields.
“automate database operations in a script or CI pipeline”
Airtable Filters Skill
urn:air:airtable.com:skill:airtable-filters
Builds Airtable filters parameters for the MCP tools that list or display records — field-type-aware comparison operators, choice and collaborator IDs, date ranges, and nested AND/OR logic. Use when the user wants to find, filter, narrow down, or search Airtable records by field values, even when they don't explicitly say "filter."
“write a filter formula to find overdue records in a database”
“filter records by multiple conditions using AND and OR logic”
“build a query to match records created in the last 7 days”
Airtable Platform Overview Skill
urn:air:airtable.com:skill:airtable-overview
Explains what Airtable is and how data is structured — bases, tables, fields, records, views, automations, and interfaces. Use when you need context about the Airtable data model.
“design a relational database schema for a business workflow”
“set up linked records between tables with rollup calculations”
“what field types should I use for a customer tracking database”
Airtable Marketing Ops Skill
urn:air:airtable.com:skill:marketing-ops
Set up and run Airtable-based marketing operations workflows — request intake, campaign orchestration, creative production, content calendars, brand and compliance review, events, localization, budgets and ROI, capacity planning. Use when the user wants a marketing request "front door," to manage campaigns, coordinate briefs and assets, build a content calendar, plan launches or events, track budgets, measure ROI, or set up agency multi-client delivery. Adapts to org size (solo marketer to enterprise multi-brand or agency) and integrates with or displaces tools like HubSpot, Marketo, Mailchimp, Klaviyo, Workfront, Asana, Monday, and Wrike. Asks scope first.
“track campaign performance and creative assets across channels”
“build an editorial pipeline from ideation to publication”
Airtable Product Ops Skill
urn:air:airtable.com:skill:product-ops
Set up and run Airtable-based product operations workflows — roadmap management, customer feedback synthesis, launch coordination, OKR cascading, sprint planning, release tracking. Use when the user wants to track product work, manage feature requests, build a roadmap, set up a feedback intake portal, prioritize initiatives, run launch checklists, or align OKRs across teams. Adapts to org size (solo founder, small team, mid-size product org, enterprise product portfolio) and existing tooling (Jira / Linear / Productboard / Aha integration; Salesforce / Zendesk / Gong feedback ingestion). Can scaffold either as a pure-Airtable workspace or as Airtable backing a custom branded UI on Vercel for public-facing portals. Asks scope questions first; doesn't impose framework. Focuses on cross-functional product operations.
“create a product roadmap with quarterly milestones and linked features”
“set up a customer feedback triage system with prioritization”
“build a sprint tracker with story points and team velocity”
Airtable Sales Ops Skill
urn:air:airtable.com:skill:sales-ops
Set up and run Airtable-based sales operations and CRM workflows — pipeline management, account and renewal management, deal desk, RFP / tender pipelines, partner CRMs, sales forecasting, vertical CRMs (real estate, mortgage, brokerage, capital markets, public works, nonprofit), and AI-native lean stacks (Clay-equivalent enrichment, AI-assisted outbound, conversation-intel ingestion). Use when the user wants to track deals, manage accounts, build a pipeline, run a deal desk, coordinate partners, manage RFPs, or build an AI-forward GTM stack. Defaults to augmenting existing CRMs (Salesforce / HubSpot); also supports Airtable-as-CRM and AI-native stacks. Asks scope first. Commercial workflows only; post-sale support belongs to a future customer-success skill.
“set up a sales pipeline with deal stages and win probability”
“build a lead qualification workflow with scoring criteria”
“create a commission tracking system for a sales team”
Airtable Link Display Skill
urn:air:airtable.com:skill:show-airtable-link
Provides a clickable Airtable link whenever the agent has touched user-visible Airtable content. Use after every MCP call that creates, updates, lists, searches, or returns records, schema, or interface pages — bases, tables, fields, records, or pages. Hand off the most-specific URL the agent's tool calls have proven access to — prefer single-record URLs over table URLs, table URLs over base URLs, and interface page URLs when the user's access is restricted to pages. Format as a markdown link with a descriptive label. Construct URLs only from IDs the tools actually returned — never synthesize IDs to round out a URL. Compose this skill from any workflow skill that affects Airtable content.
“give me a direct link to this specific record in my database”
“generate a shareable URL for this database view”
Airtable REST API
urn:air:airtable.com:api:rest
REST API for programmatic access to bases, tables, records, fields, views, webhooks, and enterprise administration. Supports OAuth 2.0 and Personal Access Tokens. Rate-limited to 5 requests/second per base.
“integrate structured data from a collaborative database into my app”
“set up webhooks to react to record changes in a database”
“programmatically create and manage database schemas via API”
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://airtable.com/.well-known/ai-catalog.json on 2026-07-31, HTTP
200. The verbatim body is stored alongside its manifest in the
Airtable repository
as ai-catalog/airtable-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.