Airtable MCP server
Airtable combines spreadsheet simplicity with database power, allowing teams to manage and organize data collaboratively. An AI agent with access to Airtable can create and modify records, query data with filters and sorting, manage file attachments, and synchronize data with external systems without manual data entry.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers.
- API credentials for the application you're connecting (see the Authentication section on this page for what to collect).
Create an MCP server
Find the app in the catalog
- Sign in to AI Gateway and select App Catalog from the left navigation.
- Search for the application you want to connect, then select it from the catalog.
- Select Create MCP Server to start the wizard.
App Configuration
Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.
MCP Server Setup
- Enter a Name for your server — something descriptive that identifies both the application and its purpose.
- Enter a Description so your team knows what the server is for.
- Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
- Select Next.
Authentication
Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.
Review
Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
Authentication
Airtable supports OAuth 2.0 (recommended for multi-user integrations) and personal access tokens (PAT) for the Web API. Register an OAuth integration in the Airtable developer hub, set the redirect URI to the value shown in AI Gateway, and request only the scopes you need. For PATs, create a token from your Airtable account and pass it as a Bearer token. You will also need a base ID (starts with app) for data operations; find it in the base’s API documentation in Airtable.
| Value | Setting |
|---|---|
| Auth endpoint | https://airtable.com/oauth2/v1/authorize |
| Token endpoint | https://airtable.com/oauth2/v1/token |
| API key header (PAT or OAuth access token) | Authorization: Bearer YOUR_TOKEN |
| Base URL | https://api.airtable.com/v0 |
| Scopes (full gateway spec) | data.records:read, data.records:write, data.recordComments:read, data.recordComments:write, schema.bases:read, schema.bases:write, user.email:read, workspacesAndBases:read |
Use a smaller subset of scopes if your integration is read-only or does not manage schema or comments. See the Airtable OAuth reference and scopes.
Available tools
This MCP server enables record operations, data querying, file attachments, schema management, and real-time synchronization with Airtable bases.
| Tool | Description |
|---|---|
| Create record | Add a new record to a table with field values |
| List records | Retrieve records from a table with filtering, sorting, and pagination |
| Get record | Fetch a specific record by ID with all field values |
| Update record | Modify field values in an existing record |
| Delete record | Remove a record from a table |
| Get table schema | Retrieve field definitions and table configuration |
| Filter records | Query records using Airtable formulas and conditions |
| Sort records | Sort results by one or multiple fields in ascending or descending order |
| Upload attachment | Add file attachments to record fields |
| Get attachments | Retrieve attachment metadata and URLs |
| Create view | Create a filtered or sorted view of table data |
| Get view records | Retrieve records as displayed in a specific view |
| Batch create | Add multiple records in a single operation |
| Batch update | Modify multiple records simultaneously |
| Count records | Get the total number of records matching criteria |
Tips
Use filterByFormula for complex queries — Airtable's filterByFormula parameter enables complex conditional queries. Learn Airtable formula syntax to filter data precisely without pulling unnecessary records.
Respect the 5 requests per second rate limit by implementing delays between requests or batch operations to stay within limits. Use batch create and batch update endpoints when modifying multiple records.
Include specific field names in requests when you only need certain fields to reduce payload size and improve performance. Don't fetch entire records if you only need a few field values.
Handle attachment URLs carefully — attachment download URLs from Airtable expire after 30 minutes. If you need to store attachments permanently, download and archive them immediately.
Plan your table structure for AI operations by designing table schemas with clear field names and consistent data types. Avoid deeply nested linked records when using the API, as they require multiple requests to traverse relationships.
Cequence AI Gateway