Skip to main content

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 individual application pages.

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 relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select 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.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

Airtable uses Personal Access Token authentication. Create a token in your Airtable Account Overview page with scopes data.records:read, data.records:write, schema.bases:read, and optionally schema.bases:write and data.recordComments:read. The API base URL is https://api.airtable.com/v0 and you'll need your base ID (starts with 'app') from the Airtable API documentation for your base. Send your token in the Authorization: Bearer YOUR_TOKEN header with all requests.

Available tools​

This MCP server enables record operations, data querying, file attachments, schema management, and real-time synchronization with Airtable bases.

ToolDescription
Create recordAdd a new record to a table with field values
List recordsRetrieve records from a table with filtering, sorting, and pagination
Get recordFetch a specific record by ID with all field values
Update recordModify field values in an existing record
Delete recordRemove a record from a table
Get table schemaRetrieve field definitions and table configuration
Filter recordsQuery records using Airtable formulas and conditions
Sort recordsSort results by one or multiple fields in ascending or descending order
Upload attachmentAdd file attachments to record fields
Get attachmentsRetrieve attachment metadata and URLs
Create viewCreate a filtered or sorted view of table data
Get view recordsRetrieve records as displayed in a specific view
Batch createAdd multiple records in a single operation
Batch updateModify multiple records simultaneously
Count recordsGet 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.