Connect Airtable to AI agents over MCP (with Stepper Skill Sets)

Let your AI agent find, create and update Airtable records through a Stepper Skill Set, limited to the actions you choose.

A Skill Set is a toolkit you build in Stepper: you connect your apps, pick which actions an agent may call, and Stepper serves them as one MCP endpoint. The agent never sees your Airtable password or API keys, and every call is logged.

Last checked:

What you can let an agent do in Airtable

These are the Airtable actions you can add to a Skill Set. They're the same actions Stepper workflows use, listed on Stepper's Airtable page. You choose which ones the agent gets.

For example, you could ask

  • Find the record for order 1042 in the Orders table and set its status to Shipped.
  • Add a record to the Suppliers table for Tidewater Clay with today's date.
  • Create Record Creates a new record with auto-populating fields.
  • Delete Record Delete a record in a table.
  • Find Record Find a record in a table.
  • Find Many Records (Advanced) Return up to 100 records as line items.
  • Update Record Update a record in a specific table.
  • Make HTTP Request Make an HTTP request to any URL with full control over method, headers, and body.

Set it up in 5 steps

You need a Stepper account, a Airtable account, and an AI client that supports remote MCP servers, such as ChatGPT, Claude, Cursor or VS Code. Your own agent works too, using a Skill Set token.

  1. Connect Airtable to Stepper

    In Stepper, connect your Airtable account. Use an account that can do what you want the agent to do, and no more.

  2. Create a Skill Set

    Go to Skill Sets in Stepper, create a Skill Set for this agent, and use Add Entry to add your Airtable connection.

  3. Restrict the actions

    Choose only the Airtable actions the agent needs. An entry with no actions chosen allows every Airtable action, so a short list is safer. To pin a value, such as one channel, table or calendar, hardcode that parameter so the agent can't change it.

  4. Add the Skill Sets server to your AI client

    Add this URL as a remote MCP server:

    https://mcp.stepper.io/skill-sets/mcp

    Then sign in to Stepper when your client asks. On the Stepper screen that follows, pick the Skill Set this agent should use. To switch to a different Skill Set later, remove the server and connect again.

    Chat apps (ChatGPT, Claude and others): add it as a custom connector or app, wherever your client lists remote MCP servers.

    Code editors (Cursor, Windsurf and others that use an mcpServers config):

    {
      "mcpServers": {
        "stepper": {
          "url": "https://mcp.stepper.io/skill-sets/mcp"
        }
      }
    }

    Your own agent or script: generate a Skill Set token in Stepper and send it as Authorization: Bearer sst_….

  5. Test it

    Ask the agent what it can do (it checks the Skill Set's list of skills) and make sure only the Airtable actions you chose appear. Then run one request using the lowest-risk action you allowed, such as a lookup or a draft, and check the call in the Skill Set's call log in Stepper.

Airtable's own MCP server, and when to use it instead

Airtable hosts its own MCP server that works with MCP clients. It follows your existing Airtable permissions, so the agent can reach the bases you can. Read Airtable's MCP server for setup.

Use Airtable's server when the agent needs to explore and edit your bases broadly and your Airtable permissions are the boundary you want.

A Skill Set fits when the agent needs Airtable alongside other apps through one endpoint, or when you want to choose exactly which actions it can call, lock parameter values, and check a log of every call.

Guardrails

An agent can misread a request, and some Airtable actions change or remove real data. Set these up before you rely on it.

Scope

Most agents only need Find Record, Create Record and Update Record. Leave Delete Record off, and lock the base and table so the agent can't reach other tables.

Use a separate Skill Set for each agent or role, so each one gets only its own actions and tokens.

Audit

Every skill call is logged with the tool name, status, how it authenticated, and when. Call logs are kept for 30 days and are visible in Stepper, so you can check what the agent did in Airtable.

Revoke

Revoke a Skill Set token from Stepper to cut off a script or client straight away. To stop an agent using one action, remove it from the Skill Set; that applies from the agent's next call, with no need to reconnect. You can also remove the server from your AI client.

Add with care: Delete Record, Make HTTP Request. Make HTTP Request can call any URL with your connection, so it gives the agent far more reach than the other actions.

Connect other apps to AI agents over MCP:

Airtable is a trademark of its owner. Stepper isn't affiliated with or endorsed by Airtable; its name is used here only to describe the integration.