You can connect Airtable to Claude in a few minutes using the Model Context Protocol (MCP), and once it’s connected, Claude can read and write records across your bases without you copying rows into the chat by hand. Airtable is also one of the more straightforward servers to connect — its OAuth just works with a new client, unlike some of the productivity tools in this series. This guide covers both ways to do it: Airtable’s official remote MCP server connected directly, and connecting it through a gateway if you use more than one AI client.

What the Airtable MCP server actually does

Airtable publishes an official remote MCP server at mcp.airtable.com/mcp. It exposes your bases, tables, and records as tools Claude can call directly. In practice that means prompts like:

  • “What’s in the ‘Q3 Launches’ base that’s still marked Not Started?”
  • “Add a new row to the Applicants table with this candidate’s details.”
  • “Summarize every record in the CRM table tagged ‘At risk.’”
  • “Update the status field on record rec0X8B to Done.”

Claude reads and writes through the same permissions your Airtable account already has — it isn’t a separate export or sync, it’s your account acting on your behalf, base by base.

Option 1: Connect Airtable to Claude directly

Claude supports remote MCP servers natively. The short version of the setup:

  • Open Claude’s connector or MCP settings.
  • Add a remote server pointing at Airtable’s MCP endpoint.
  • Sign in with your Airtable account when prompted — this is standard OAuth, so Claude never sees your Airtable password, and you can revoke access from Airtable’s own account settings at any time.

That’s enough for one person using Airtable inside Claude. The tradeoffs show up once you add a second tool or a second person: every additional AI client (ChatGPT, Cursor, an agent) needs its own copy of that same connection, its own OAuth grant, and its own place where the config can go stale or get lost.

Option 2: Connect it once, through a gateway

If you’re already juggling more than one MCP server, or more than one AI client, wiring each pair directly gets old fast — that’s the connection sprawl we wrote about in what an MCP gateway is. The alternative is connecting Airtable (and everything else) to one gateway URL, then pointing every AI client at that single URL instead of reconfiguring each one.

With gate specifically, connecting Airtable looks like this: add gate’s gateway URL to Claude once, then pick Airtable from the Airtable server page in the directory and sign in with OAuth the same way you would directly. From then on, Airtable’s tools are available in every client connected to your gate URL — Claude, ChatGPT, or Cursor — without a second setup step. You can see the full list of servers set up this way on the MCP servers page.

Why the connection method matters for a database like Airtable

Airtable often holds more than one team’s data in a single account — a CRM base, an HR base, a product roadmap — each with its own sensitivity. A few things worth checking before or right after you connect:

  • Is it the official endpoint? Connect Airtable’s documented server (mcp.airtable.com), not a third-party mirror claiming to proxy it.
  • Which bases can it actually reach? An MCP connection to Airtable typically covers every base your account can open, not just the one you had in mind. Know what’s in scope before you hand Claude a broad prompt against “the workspace.”
  • What can it write, not just read? A base with write access can have records created, edited, or deleted at whatever pace it’s prompted to. If a base doubles as a system of record for something important, treat write access to it with the same caution as any other production data.
  • Who else on your team can reach it? If more than one teammate connects Airtable to their own AI client, you likely want a shared, revocable setup rather than everyone holding their own token — the same access-control question we cover in MCP access control for teams.

You can run a quick, no-signup check on any server’s tool list — including ones that require OAuth, once connected — with gate’s free MCP security scanner, which looks for prompt injection and hidden instructions in tool descriptions before you rely on a server day to day.

Troubleshooting the connection

A few things that commonly go wrong when connecting any remote MCP server, Airtable included:

  • OAuth loop or sign-in fails. Make sure you’re signed into the right Airtable account in your browser before authorizing — a mismatched account or workspace is the most common cause.
  • Claude can’t find a base you know exists. Airtable’s tools respect your permissions in Airtable itself — if a base lives in a workspace you don’t have access to, Claude won’t see it either.
  • Tools disappear after an Airtable update. Remote servers can change their tool list without warning. If you’re connected through a gateway, that kind of change is exactly what drift detection is meant to catch.

The bottom line

Connecting Airtable to Claude with MCP takes a few minutes either way: point Claude directly at Airtable’s server and sign in, or connect it once through a gateway if you want the same Airtable access available in every AI client you use, with the server’s tools checked before they go live. Either way, treat the OAuth grant for a database that spans multiple bases the same way you’d treat any other tool with broad write access — worth a minute’s thought before you say yes.