How to connect an Airtable MCP to Cursor (4 steps)

Airtable's fields aren't uniform.

Select fields carry specific option values, linked records reference rows in other tables by record ID, and formula or rollup fields return computed values you can't predict from the base's UI, and more.

Before you can write a sync, you need to see a real record, and before you map a linked field, you need to see how the reference actually comes back.

Each of those checks means leaving the editor for Airtable's API documentation or a scratch script and carrying the answer back in a browser tab.

To help your developers query Airtable data without leaving Cursor, we'll show you how to connect Airtable with Merge Agent Handler's Airtable MCP server.

How it works

Merge Agent Handler connects Cursor to Airtable's API through the Merge CLI.

You'd install the CLI, authenticate once, and run a single setup command from your project root.

That command writes a ## Merge CLI section to your project's .cursorrules file, which tells Cursor's agent when to call merge search-tools and merge execute-tool to reach Airtable.

Merge will also manage your Airtable OAuth token storage and refresh on your behalf, so no credential state lives in your local environment.

Related: How to use the Airtable MCP in Claude Code

Prerequisites

Before getting started, you'll need the following:

• A Merge Agent Handler account
• Cursor installed
• pipx installed (run pipx --version to confirm, or install via pip install pipx)
• An Airtable account with access to the bases you want to connect

If you want to connect Merge Agent Handler's Airtable MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

1. Install the Merge CLI

Add the Merge CLI to your environment with pipx: pipx install merge-api

Confirm the installation succeeded: merge --version

2. Log in to Merge

Connect the CLI to your Merge Agent Handler account: merge login

This links the CLI to your account so Merge can make authorized requests against Airtable on your behalf.

3. Connect the CLI to Cursor

Run the following from the root of the project where you want to use Merge tools:

merge setup cursor

This writes a ## Merge CLI section to .cursorrules so Cursor knows to use the CLI for third-party services. The command is idempotent, so it's safe to re-run if you need to reset.

Related: Steps for connecting an Airtable MCP with Codex

4. Authenticate Airtable

Open a Cursor chat in your project and try a prompt such as:

Fetch one record from my launches table and show every field it returns, including any linked records, attachments, and select field options, so I can model it correctly before writing the sync.

The first time you invoke an Airtable tool, a Magic Link will appear to complete connector authentication.

{{this-blog-only-cta}}

Airtable MCP FAQ

In case you have more questions on setting up and using the Airtable MCP in Cursor, we've addressed several more commonly-asked questions below.

What can you do once the Airtable MCP is connected to Cursor?

With Airtable connected, Cursor can:

• Inspect a real record before writing a parser: fetch a record to see the exact field types it returns, including linked record arrays and attachment objects, so your deserialization code matches the real response

• Pull a table's field schema before modeling it: fetch the field definitions for a table, including each select field's actual option values, so your type definitions match the API instead of a guess

• Resolve real record and field IDs: get the actual record ID format and field IDs your integration will reference, so you don't hardcode values that fail to resolve at runtime

• Inspect linked record and rollup fields before writing traversal code: see how a linked record references rows in another table and how rollup or lookup values are computed before you write the code that follows those references

• Check the attachment object shape before writing upload or download code: retrieve a record with an attachment field to see the URL, thumbnail, and size structure before you write the code that processes it

• Validate pagination on a real base: run a query that returns many records to see how the offset parameter comes back before you implement your pagination loop

Why use Merge Agent Handler vs. a self-hosted Airtable MCP server?

You can self-host an Airtable MCP server using open-source packages that wrap the API directly. For a solo developer working against their own base, that setup works: generate a personal access token, stand up the server, and point Cursor at it.

The overhead compounds at the team level.

Airtable auth means managing personal access tokens or OAuth credentials, keeping them scoped correctly, and making sure they survive process restarts. If several developers need Airtable access through Cursor, each one manages their own token or they get shared in ways that are hard to audit and revoke cleanly. There's no built-in way to scope which bases or operations a given agent can reach.

Merge Agent Handler centralizes authentication and adds a control layer on top.

You define which Airtable operations each agent is allowed to call, Merge enforces those boundaries, and every tool call is logged with a full audit trail that includes the input and output.

Why connect Airtable to Cursor?

Developers writing Airtable integrations have to understand its data model before the code will work: typed fields that don't map one-to-one to simple values, linked records that reference other tables by ID, and attachments and computed fields with their own response shape.

That structure is documented, but reading about it isn't the same as seeing a real record from the base your integration will run against.

With the Airtable MCP connected, Cursor can pull real Airtable data directly in the chat panel.

You can fetch a record while writing the parser that will process it, check a field schema while writing the model it maps to, or resolve real record IDs while writing the calls that use them.

The data your code depends on and the code itself live in the same session, which cuts the round-trip to the API docs or a separate test script.

Can I use Merge Agent Handler's Airtable MCP with my employees?

Yes, Agent Handler for Employees is built to help organizations provision, secure, and govern how employees connect AI tools like Cursor to systems like Airtable.

Common patterns include:

• Provisioning and access control via SCIM with identity providers like Okta and Microsoft Entra ID, so IT can manage which bases an employee's agent can reach by role or team

• DLP and policy enforcement on tool calls, so admins can block queries that would return sensitive record data before results reach the editor session

• User-level audit logging so security and IT teams can review which records were viewed, created, or updated, by which employee identity, and when

Put together, employees can use the Airtable MCP to write syncs against real field schemas, build integrations grounded in actual linked record structure, validate data against real select options, and more, while IT keeps centralized control over which bases each agent can reach.