Airtable MCP Server: What It Does and How to Connect Airtable to AI in 2026
Yes — Airtable has an official MCP server. It lives at mcp.airtable.com, and it lets any MCP-compatible AI tool read and write your bases directly: records, tables, fields, and even whole new bases. So if you’re searching “Airtable MCP,” the connection you want already exists and it comes straight from Airtable.
The thing worth knowing before you set it up: an MCP server hands your bases to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches Airtable for you, nothing fires when a record changes, and nothing runs while the chat is closed. Here’s exactly what the Airtable MCP does, how to turn it on, where it stops — and what to use when you want Airtable work that runs on its own.
What the Airtable MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, Claude Code, Codex, Amazon Q, and others — talk to an outside app through a shared interface. Airtable’s official server, at mcp.airtable.com, gives an MCP-compatible AI read and write access to your bases, respecting whatever permissions your account already has.
With it connected, an AI client can:
- Look up records — “pull every row in the Q3 pipeline table where status is Overdue” answered from your live base.
- Create and update — add a record, change a field value, or update a table’s schema without opening Airtable.
- Build structure — create a new base, table, or field on the fly, including setting up a base from scratch in a workspace you have Creator access to.
- Reason across data — summarize a base, spot missing values, draft a report from actual records instead of a guess.
It’s genuinely useful for ad-hoc work: ask a question, get an answer grounded in your data, make a change on the spot.
How to set up the Airtable MCP server
The official server is the quick path — no code, no hosting:
- In your AI client’s connector settings, add a remote MCP server pointing at
https://mcp.airtable.com/mcp. - Authorize it through the OAuth prompt (the recommended method) — or, for manual client setup, pass a personal access token as an
Authorization: Bearerheader. - Confirm the tools appear in the client, then start a chat and ask it to read or update a base.
If your workspace has admin restrictions on third-party integrations, an admin will need to allowlist the MCP connection first. Airtable’s own support docs cover the full setup for each supported client.
Where the Airtable MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch your base; it waits for you to ask.
- No triggers. A new record landing in a table, a status field flipping to “Done,” a linked record changing — none of these can start anything through MCP. There’s no “when this happens in Airtable, do that.”
- It’s one app at a time. The Airtable MCP knows Airtable. Getting a new record into Slack, Gmail, and a Google Sheet means wiring up (and authing) a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. OAuth tokens, personal access tokens, and the blast radius of read/write access to your bases are all on you.
So the Airtable MCP is a great way to ask your base things and make one-off edits. It is not a way to make Airtable run — to have work happen on a schedule or in reaction to an event, across the other tools a record touches.
Running Airtable work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Airtable natively — no MCP server to host, no OAuth plumbing to maintain — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Airtable work happens whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a new record lands in your intake table → enrich it, route it to the right table based on its fields, and post a summary to Slack — automatically, the moment it arrives.
- Every Monday morning → pull every record with a status of “Overdue,” summarize them, and email the list to the owner.
- When a record’s status changes to “Approved” → create the matching row in your accounting tool and draft a confirmation email for review.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Airtable connection and everything downstream.
If you just want to interrogate a base from a chat, Airtable’s official MCP server is the right tool and it’s free to connect. If you want Airtable to actually do things — on a trigger, on a schedule, across every app a record flows through — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does Airtable have an official MCP server?
Yes. Airtable publishes and maintains its own MCP server at mcp.airtable.com, giving MCP-compatible AI tools read/write access to bases, tables, records, and fields.
Is the Airtable MCP server free? Connecting it is free — you’re authorizing an AI client against your existing Airtable account and permissions. You still need whatever Airtable plan your bases live on.
Can the Airtable MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Airtable work across apps, you need a workflow tool like Carly rather than an MCP server.
What AI tools can connect to Airtable over MCP? Any MCP-compatible client — Claude, ChatGPT, Cursor, Claude Code, Codex, Amazon Q, and others — can connect to Airtable’s official MCP server.
Can I connect Airtable to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Airtable for you and lets you build the automation in plain language — describe what you want to happen and it wires up the base and the other apps involved, with no server to host and no code to write.
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
