How to connect to the Airtable MCP with Claude Code (5 steps)
.png)
Airtable has become the structured data layer for many non-engineering teams: product roadmaps, content calendars, launch checklists, customer research.
Developers who need to build agents around that data spend too much time writing one-off API calls or exporting CSVs, when what they actually need is a live connection from their coding session directly into the base.
To help your developers read, search, and update Airtable records directly from their coding sessions, we'll show you how to connect Airtable with Merge Agent Handler's Airtable MCP server.
How it works
Merge Agent Handler acts as a secure bridge between Claude Code and Airtable's API. When you configure a Tool Pack and Registered User, Merge generates a unique MCP URL that Claude Code accesses via HTTP, combined with an API key for authentication.
Here's how the command looks before you add your specific MCP URL and API key:
Claude Code sends requests to that MCP URL, and Merge handles authentication and API calls to Airtable on the backend. You don't manage Airtable personal access tokens or OAuth credentials locally. Merge handles token storage and refresh from here on.
Prerequisites
Before getting started, you'll need the following:
- A Merge Agent Handler account
- Claude Code installed (run <code class="blog_inline-code">
claude --version</code>to confirm) - An Airtable account with access to the bases you want to connect
Related: A guide to integrating Jira MCP with Claude Code
1. Create a Tool Pack
Log into Merge Agent Handler and navigate to Tool Packs. Click Create Tool Pack and give it a name tied to the use case, like Record updater agent.

Under connectors, select Airtable. Choose which tools to enable.

For most workflows, enabling record search, record retrieval, and table listing covers the common cases. Enable write tools if you want your agent to create or update records directly.
Save the Tool Pack. You'll return here in step 4 to copy your MCP URL.
2. Add a Registered User
Inside your Tool Pack, create a Registered User. This is the identity context under which your agent operates: the account it acts on behalf of when calling Airtable's API.

Give it a name that maps to your environment, like dev-local or your own name. Once created, Merge generates a unique MCP URL scoped to this user.
3. Authenticate Airtable
From the Registered User detail page, click Add Connector and select Airtable. This kicks off the authentication flow.

Sign in with the Airtable account that has access to the bases you want Claude Code to reach, and grant the requested permissions.
Once authenticated, Merge stores and manages the credentials. You won't need to re-authenticate unless you revoke access.
4. Gather your credentials
You need two things before configuring Claude Code:
1. MCP URL: found on the Tool Pack detail page under the Registered User you just created. It looks like this:
2. API key: found in Settings > API Keys in your Merge Agent Handler dashboard. Create one if you don't have one yet.
Keep both handy for the next step.
5. Configure Claude Code with Airtable
Run the following command in your terminal, substituting your actual MCP URL and API key:
Verify the connection registered with the command <code class="blog_inline-code">claude mcp list</code>.
<code class="blog_inline-code">agent-handler</code> should appear in the output with a connected status.
To confirm the connector is accessible, open a Claude Code session and make an ask like "List all tables in my product roadmap Airtable base and show me the records in the current quarter view."
You should then see an output that looks something as follows:

{{this-blog-only-cta}}
Airtable MCP FAQ
In case you have more questions on setting up and using the Airtable MCP in Claude Code, we've addressed several more commonly-asked questions below.
What can you do once the Airtable MCP is connected to Claude Code?
With Airtable connected, Claude Code can:
- Search and retrieve records: pull up rows from any table by field value, view, or filter criteria without leaving the terminal
- List tables and bases: surface the schema and available views for any base your agent has access to
- Read record detail: fetch full field values for any record, including linked records, attachments, and formula outputs
- Create new records: add rows to any table directly from Claude Code if write tools are enabled
- Update existing records: modify field values on existing rows to reflect new status, decisions, or data
- Cross-reference bases: retrieve records across multiple tables in a single session to support more complex agent workflows
Why use Merge Agent Handler vs. a self-hosted Airtable MCP server?
You can build a self-hosted MCP server that calls Airtable's API directly. For a solo developer connecting to their own workspace, that approach is manageable.
It breaks down at the team level. Self-hosting means each developer manages their own Airtable personal access token, you have no central visibility into what agents are reading or writing across your bases, and you're responsible for maintaining the server as Airtable's API evolves. Token rotation when someone offboards is a manual process with no audit trail.
Merge Agent Handler is a managed MCP layer. It centralizes authentication, scopes access per Tool Pack and Registered User so each agent only touches the bases you explicitly allow, and logs every tool call. When you need to audit what an agent queried or modified in Airtable, the record is there.
For teams building agents that read or write production Airtable data, Merge Agent Handler removes the per-developer credential problem and adds the access controls that matter in shared environments.
Why connect Airtable to Claude Code?
Airtable is where structured business data lives outside engineering systems. Claude Code is where developers build the agents that need it. The gap between them forces a workaround: exporting CSVs, writing one-off API scripts, or re-scraping data whenever the base changes.
With the Airtable MCP connected, Claude Code can query that data directly. You can build an agent that pulls feature specs from a roadmap base, reads acceptance criteria, and uses them as context for writing code, all in one session. Engineers stop being blocked by data that lives in the wrong tool. The work and the data are finally in the same place.



.png)
