Using the Airtable MCP server
Last updated: August 10, 2026
Plan availability | All plans |
Permissions | Your MCP permissions mirror the same permission level(s) that you have have been granted in Airtable.
|
Platform(s) | Works with AI assistants that support Model Context Protocol (Claude, ChatGPT, and other MCP-compatible tools) |
Airtable’s MCP server lets you connect AI tools directly to your Airtable bases. This integration allows you to ask questions about your data, create and update records, and analyze information—all through natural conversation with AI tools like Claude, ChatGPT, Cursor, and more.
Setup instructions, client quickstart guides, and full technical documentation are available at Airtable developer docs: MCP server overview. Start there to connect Claude, ChatGPT, Claude Code, Cursor, or any other MCP-compatible tool.
What is Model Context Protocol (MCP)?
Model Context Protocol (MCP) is an open standard that allows AI tools to securely connect to external data sources. With MCP, AI tools can query your Airtable data, perform actions on your behalf, and present structured information—all while respecting your existing permissions and security settings.
What you can do with MCP?
The Airtable MCP Server enables several types of interactions between your AI tools and your data. Below is a brief list of capabilities, but you can find more information in the developer docs here.
Search and analyze data—"Show me all customers from our CRM base who haven't been contacted in the last 30 days."
Create records—"Add these 5 new project tasks to my Project Tracker base."
Update existing records—"Update the status of task #123 to 'Complete'."
Create bases—"Create a new base called 'Q3 Campaign Tracker' in my Marketing workspace."
Access interface data—"Show me the records from the Q1 Pipeline page" (works even with interface-only permissions).
Create interfaces and interface pages—"Create an interface page to track my open tasks."
Work with automations - “What automations are configured in my Project Tracker base?”
MCP prerequisites
Before setting up the Airtable MCP Server, you'll need:
An MCP-enabled Host (Claude, ChatGPT, Cursor, etc)
Data stored in Airtable bases
Permission to use third-party integrations in your Airtable organization (if you don’t have permission, an Airtable admin at your organization may need to allow-list a new integration)
Tips for optimal MCP usage
Get the most out of your MCP integration with these tips:
Be specific: When asking about data, mention the base name or describe what you're looking for clearly
Use natural language: You don't need to know field names or table IDs—describe what you want in plain English. Sometimes you may want to describe the base in more detail before asking for data from a table.
Check permissions: If you can't access certain data via MCP, verify that you have the appropriate permissions in Airtable.
Think about what data you’re giving your AI tool: Your tool will be able to read and make edits to your Airtable data on your behalf. Make sure you trust the tools you’re using or any other data sources you connect to.
Setting up a quick MCP connection
All setup paths—pre-built connectors, plugins, manual OAuth configuration, and personal access tokens—are documented in the developer docs:
Before setting up, you'll need an MCP-enabled AI tool, data stored in Airtable bases, and permission to use third-party integrations in your Airtable organization. If you don't have permission, an Airtable admin may need to allowlist the integration—see the FAQs below.
Managing your MCP integration
After setup, you can control which bases your AI assistant can access:
Go to your third-party integrations page.
Alternatively, click your user profile in Airtable, then click Integrations and Third-party integrations.
Select your MCP integration.
Add or remove bases and apps as needed. You can also add apps where you have interface-only access.
Limitations and dependencies
Keep these limitations in mind while using the MCP Server:
Rate limits: MCP server calls are subject to standard Airtable API rate limits.
Batch size: Creating records is limited to 10 records per request.
Change policy: Tool names, behaviors, and capabilities may change
Permission requirements: The MCP server respects your existing Airtable permissions—you can only access data you normally have permission to view or modify.
Third-party integrations: If you are an enterprise user and your admin has enabled restrictions on third-party integrations, they'll need to allowlist the MCP integration.
Automation activation: MCP can create and update automation drafts, but turning an automation on (deploy) is done in the Airtable UI.
FAQs
Can I use MCP with any base I have access to?
If you have base-level access, you can use MCP to access the data stored within that base. The MCP server respects your existing Airtable permissions. If you have read-only or comment-only access to a base, you'll be able to read that data via MCP, but you won't be able to create or update records.
What AI assistants work with Airtable's MCP Server?
Any AI assistant that supports the Model Context Protocol can connect to Airtable's MCP Server. This includes Claude, ChatGPT, and other MCP-compatible tools. Check your AI assistant's documentation to confirm MCP support.
How do I revoke access if I no longer want my AI assistant to access my bases?
Navigate to your user profile > Integrations > Third-party Integrations, find the MCP integration, and either remove specific bases or delete the integration entirely.
Does using MCP count against my Airtable limits?
MCP uses our public API under the hood and will count against any existing API rate limits. Any records created using MCP will count against existing base limits.
Can I use MCP to access Airtable Interfaces?
Yes. If you have interface-only access to a base, you can use MCP to discover your interface pages (list_pages_for_base), list records shown on a page (list_records_for_page), and drill into record details (get_record_for_page). The data returned respects the same permissions as your interface — you'll only see data that your interface pages make available to you.
What happens if I try to update a field I don't have permission to modify?
The MCP server will return an error, just as the Airtable API would. Your AI assistant should communicate this limitation to you.
Are there additional costs for using MCP?
No. The MCP integration is currently included with your current Airtable plan. There are no additional Airtable charges for MCP usage, but existing API rate limits remain.
How can admins enable a blocked MCP integration?
For Airtable admins to enable a blocked integration:
Navigate to Admin Panel > Settings > Integrations & development > Third party integration allowlist.
Click Allow integration.
Enter the client ID provided by your user.
Click Save.
Can I create new bases using MCP?
Yes. You can use the create_base tool to create a new base in any workspace where you have Creator-level permissions. You can optionally define tables and fields during creation. Use list_workspaces first to find the workspace ID where you want to create the base.
Can the Airtable MCP connect to development apps (part of the managed apps and components feature) and update those apps in the same way as regular Airtable bases?
No. Calls to a development base will return a 403 permissions error. However, API/MCP calls can be made to bases where a managed app or component has been installed (i.e., the child/production bases). So the restriction is specifically on the development base itself, not on installed instances.
How do I connect Claude Code to Airtable?
The recommended approach is to run claude mcp add --transport http airtable https://mcp.airtable.com/mcp in your terminal, then run /mcp inside Claude Code to authenticate with your Airtable account through your browser. Alternatively, you can connect using a personal access token if you prefer — see the Personal Access Token section above for instructions.
Who at my organization can enable third-party integrations or MCP, and can Airtable tell me who my admin is?
Allowlisting a third-party integration is handled by an admin at your own organization. Typically that person is a super admin, org unit admin, or an integration admin with access to the “Settings → Integrations & development” in the admin panel. For the exact steps, see "How can admins enable a blocked MCP integration?" above.
For privacy and security reasons, Airtable Support does not share the names or contact details of admins within an enterprise account. To find the right person, reach out to your internal IT team or whoever manages your organization's Airtable account. If your first contact isn't able to make an organization-wide decision, they can usually point you to the person who can.
I have Editor permissions but can only create an "Interface only" token. Why?
If you are only able to create "Interface only" tokens, that usually means you have Editor access to an interface, not to the underlying base. Interface access and base access are separate in Airtable, and full-access tokens — including the kind needed to connect an MCP client like Claude in edit mode — require base-level access.
To resolve it, ask a base owner, creator, or an admin in your organization to grant you Editor (or higher) access to the base itself, not just the interface. Base access is shared through a base invite link, which works differently from interface sharing — see Creating Airtable base share links. Once you have base-level access, the full-access token option will become available.
How do I limit write access when setting up an MCP connection?
For a read-only connection, so your AI tool can view data but can't create, update, or delete records, include only these scopes:
data.records:readschema.bases:readdata.recordComments:readworkspacesAndBases:read
Enterprise admins should refer to this section to utilize a service account to accomplish this setup.
Can I create or edit automations using MCP?
Yes. You can list and inspect automations, create draft automations, update draft configuration, and delete inactive automations. New and updated automations are saved as drafts—open the automation in Airtable to review and turn it on. To delete an automation that is currently on, turn it off in Airtable first.