Does this MCP handle complex field types like attachments?

Yes. The capabilities are designed to handle complex field types and attachments, allowing your agent to manage them directly within the workflow.

What is the difference between listing records and getting a single record?

Using list_airtable_records pulls a set of records, letting your agent review multiple entries. get_airtable_record is for pulling the detailed metadata of one specific record by its ID.

Can I use this with my existing Airtable base structure?

Absolutely. The agent first uses the schema discovery capability to read your base architecture, so it knows exactly how your tables, fields, and views are set up.

Is this just a read-only connector?

No. This MCP gives your AI agent full write access. It can create, update, and delete records, making it a powerful operational capability.

How do I find my Airtable Personal Access Token?

Log in to your account, navigate to the Developer Hub, and click Create token. Ensure you grant data.records:read, data.records:write, and schema.bases:read scopes.

Can I filter records using formulas via AI?

Yes! The list_airtable_records capability accepts a filter_by_formula parameter where you can provide native Airtable query logic programmatically.

How do I find my Base and Table IDs?

Base IDs are found in the URL (starts with 'app'). You can use the get_airtable_base_schema capability to retrieve Table IDs and field names programmatically.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Airtable (Alternative) to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Let your AI agent manage records and workflows directly.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Airtable.

01
Get airtable base schema
Get base schema
02
Get airtable record
Get a specific record
03
List airtable comments
List comments on a record
04
Update airtable record
Update a record

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Airtable.

05
Create airtable records
Must pass a JSON array of objects with a "fields" key. Create new records
06
Delete airtable record
Delete a record
07
List airtable records
List records in a table

Real work

What teams actually run

Lead Status Updates

An operations manager can ask the agent to find all leads marked 'Needs Follow-up' and update their status to 'Contacted' in one go.

Project Audit

A project manager needs to know the full history of a client. The agent retrieves the record, then pulls all associated comments and interactions.

New Data Ingestion

A developer can ask the agent to take a list of new contacts and create multiple records in the 'Leads' table, passing all necessary fields.

Base Structure Review

Before building a new workflow, the agent uses the schema discovery capability to map out every table and field type in the base.

Automate a task

Put Airtable to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Airtable works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Airtable to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

967ms average. Fast in production.

Airtable is checked daily against the live service.

Daily averagePeak 1208ms

Oct 3Today

Fastest day: 830ms
Slowest day: 1208ms
14-day trend: Slowing+13%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Airtable, so you can see the experience inside your AI.

It does not authenticate your account with Airtable. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Airtable Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_xFvTCMGzUvQ6HbRdUwXKHsWQTqlmtioHtyFh5UPp/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Airtable capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "airtable-alternative-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_xFvTCMGzUvQ6HbRdUwXKHsWQTqlmtioHtyFh5UPp/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Airtable in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Airtable owners hand off.

This MCP is for teams that rely on Airtable for operational data but need more than just a spreadsheet. It lets your AI agent handle the complex, multi-step data tasks that used to require manual work or custom scripting.

01
Operations Teams
Use the agent to instantly pull lead records and update statuses across bases using natural language commands.
02
Project Managers
Track project milestones and coordinate team comments without leaving your primary workspace.
03
Developers
Integrate high-speed, low-code data structures into custom AI workflows through simple, direct AI queries.

FAQ

Questions Airtable owners ask.

01
Does this MCP handle complex field types like attachments?
Yes. The capabilities are designed to handle complex field types and attachments, allowing your agent to manage them directly within the workflow.
02
What is the difference between listing records and getting a single record?
Using list_airtable_records pulls a set of records, letting your agent review multiple entries. get_airtable_record is for pulling the detailed metadata of one specific record by its ID.
03
Can I use this with my existing Airtable base structure?
Absolutely. The agent first uses the schema discovery capability to read your base architecture, so it knows exactly how your tables, fields, and views are set up.
04
Is this just a read-only connector?
No. This MCP gives your AI agent full write access. It can create, update, and delete records, making it a powerful operational capability.
05
How do I find my Airtable Personal Access Token?
Log in to your account, navigate to the Developer Hub, and click Create token. Ensure you grant data.records:read, data.records:write, and schema.bases:read scopes.
06
Can I filter records using formulas via AI?
Yes! The list_airtable_records capability accepts a filter_by_formula parameter where you can provide native Airtable query logic programmatically.
07
How do I find my Base and Table IDs?
Base IDs are found in the URL (starts with 'app'). You can use the get_airtable_base_schema capability to retrieve Table IDs and field names programmatically.

Explore

More in Loved By Devs

Connect Airtable to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Get airtable base schema

Get airtable record

List airtable comments

Update airtable record

05-07

Create airtable records

Delete airtable record

List airtable records

What teams actually run

Lead Status Updates

Project Audit

New Data Ingestion

Base Structure Review

Building your own app? The connector is yours to use.

Airtable Connector

Claude Desktop

Operations Teams

Project Managers

Developers

Does this MCP handle complex field types like attachments?

What is the difference between listing records and getting a single record?

Can I use this with my existing Airtable base structure?

Is this just a read-only connector?

How do I find my Airtable Personal Access Token?

Can I filter records using formulas via AI?

How do I find my Base and Table IDs?

Data Pipeline Prover AI Connector

Feishu Bitable AI Connector

Airtable AI Connector

SeaTable AI Connector

Suggestions

data.world AI Connector

Hevo Data (ETL & Data Pipeline) AI Connector

Baserow AI Connector

Baserow AI Connector