Quickly list bases and tables, explore your full base, and work with records using filters, sorts, selected fields, and metadata.
What is Airtable MCP?
The Airtable MCP node gives AI-powered access to your Airtable account. Describe what you need, and the node performs the action, returning structured data you can pass to other steps. It is designed for reuse in automated workflows and works best with focused, single-action prompts.What Can It Do for You?
- Retrieve records with precise filters, sorts, and selected fields
- Create, update, or delete records to keep your tables current
- Explore your workspace by listing bases, tables, and detailed base schema
- Manage structure by updating tables and creating or modifying fields
Available Tools
Tool | What It Does | Example Use |
---|---|---|
List Records | List records in an Airtable table with filtering, sorting, field selection, and metadata options | ”In base base name , list records from table table name where field name equals value , sort by sort field sort order , and return structured data with id and field names to return ” |
Create Records | Create new records in an Airtable table | ”In base base name , create a new record in table table name with fields field1 =value1 , field2 =value2 , and return structured data with the new record id” |
Update Records | Update existing records in an Airtable table | ”For records with ids record ids , update field name to new value in table table name and return structured data with updated ids” |
List Bases | List all accessible Airtable bases with their id, name, and permission level | ”List all accessible bases and return structured data with name, id, and permission level” |
List Tables | List all tables in a given Airtable base | ”In base base name , list tables and return structured data with table name and id” |
Base Schema | Get detailed schema for all tables in a base | ”In base base name , return structured data for all tables including each table name and its fields and types” |
Get Record | Get a single record by its id from a table | ”Get record with id record id from table table name and return structured data for all fields” |
Delete Records | Delete one or more records from a table | ”Delete records with ids record ids from table table name and return structured data with deleted ids” |
Update Table | Update an existing table’s name or description | ”In base base name , update table table name description to new description and return structured data with updated table metadata” |
Create Field | Add a new field (column) to an existing table | ”In base base name and table table name , add a field named new field name of type field type , and return structured data with field id and name” |
Update Field | Update a field’s metadata in a table | ”In base base name , table table name , update field field name to type new type and return structured data with updated field metadata” |
List Comments | List all comments for a specific record from newest to oldest | ”For record id record id , list comments from newest to oldest and return structured data for each comment” |
How to Use
1
Create Your Airtable MCP Node
Go to your node library, search for Airtable, and click “Create a node with AI”
2
Add Your Prompt
Drag the Airtable MCP node to your canvas and add your prompt in the text box. Keep it focused on a single action and use variables like
base name
, table name
, or field name
.3
Test Your Node
Run the node to see the results. If it works as expected, you’re all set. If you run into issues, check the troubleshooting tips below.
4
Save and Reuse
Once your Airtable MCP node is working, save it to your library. You can now use this customized node in any workflow.
Example Prompts
Here are some prompts that work well with Airtable MCP: Discover Your Workspace:Start simple and keep each node focused on one action. Use one node to fetch ids or schema, then pass those values into a second node for updates or deletes. The structured data output makes it easy to connect steps.
Troubleshooting
If your Airtable MCP node isn’t working as expected, try these best practices:Keep Prompts Simple and Specific
- Good: “In base
base name
, list records from tabletable name
wherefield name
equalsvalue
and return id andanother field name
” - Needs improvement: “Find records across multiple tables, update them, and also create new ones if missing”
For best results, create separate nodes for each action. Airtable MCP works best with focused, single-action prompts.
Match What Airtable Can Do
- Good: “Create a record in table
table name
with fieldsfield1
=value1
,field2
=value2
and return the new record id” - Needs improvement: “Analyze the records, create a dashboard, and email a summary to
recipient email
”
Airtable MCP excels at managing Airtable data. For analysis or summaries, add Ask AI, and for emailing connect Gmail Sender node in your workflow.
Break Complex Tasks Into Steps
Instead of trying to do everything in one prompt (which might cause timeouts or errors):1
Step 1: Get Record IDs
In base
base name
, list records from table table name
where status
equals Open
and return structured data with record ids2
Step 2: Update Records
For records with ids
record ids
, update status
to In Progress
in table table name
and return structured data with updated ids3
Step 3: Manage Structure
In base
base name
and table table name
, create a field named Processed At
of type date
and return structured data with field id and nameConnect these nodes sequentially. The record ids output from Step 1 become the input for Step 2, and the table identifiers for Step 3 come from your base and table discovery steps.
Focus on Data Retrieval
Airtable MCP is great at getting information from Airtable. For analysis or summaries, combine it with the Ask AI node. Example:- Good prompt: “List records from table
table name
wherepriority
equalsHigh
and return structured data with id andowner
” - Needs improvement: “List high priority records and generate a weekly summary report”
Use Ask AI for analysis or summarization. Keep Airtable MCP focused on retrieving and updating Airtable data, then pass the structured data to Ask AI for the report.
Troubleshooting Node Creation
Empty Outputs
Empty Outputs
If you’re seeing empty outputs in the node creation window (or if you’ve already created the node, hover over it and click “Edit”), use the chat interface to prompt the AI to add debug logs and verify the API response. Specifically mention that you received empty outputs.
Incorrect Results
Incorrect Results
In the node creation window (or if you’ve already created the node, hover over it and click “Edit”), use the chat interface to describe in detail what you expected versus what you received.
Errors
Errors
First click “Fix with Gummie”. If multiple attempts fail, simplify your prompt or contact support. You can also click the “Request changes” button in the node creation window for additional guidance.
Iterate Using the Chat
Iterate Using the Chat
MCP node creation often requires a few tweaks. Use the chat interface in the node creation window to refine filters, output fields, or pagination. The AI will adjust the node based on your feedback.
Need More Help?
- Watch What are MCP Nodes video tutorial
- Check out MCP Best Practices in Gumloop University
- Join the Gumloop Community for support
- View the Airtable MCP setup guide for Claude and Cursor
- Contact support at support@gumloop.com