mcp/airtable-mcp-server repository overview

⁠Airtable MCP Server

Provides AI assistants with direct access to Airtable bases, allowing them to read schemas, query records, and interact with your Airtable data. Supports listing bases, retrieving table structures, and searching through records to help automate workflows and answer questions about your organized data.

What is an MCP Server?⁠

⁠MCP Info

⁠Image Building Info

Attribute	Details
Dockerfile	https://github.com/domdomegg/airtable-mcp-server/blob/2a5896d0891d13558e1313155b177fc0a4bc95d6/Dockerfile⁠
Commit	2a5896d0891d13558e1313155b177fc0a4bc95d6
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/airtable-mcp-server --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	MIT License

⁠Available Tools (16)

⁠Tools Details

⁠Tool: create_comment

Create a comment on a record

⁠Tool: create_field

Create a new field in a table

⁠Tool: create_record

Create a new record in a table

⁠Tool: create_table

Create a new table in a base

⁠Tool: delete_records

Delete records from a table

This tool may perform destructive updates.

⁠Tool: describe_table

Get detailed information about a specific table

• tableIdentifiersOnly: table IDs and names
• identifiersOnly: table, field, and view IDs and names
• full: complete details including field types, descriptions, and configurations

Note for LLMs: To optimize context window usage, request the minimum detail level needed:

• Use 'tableIdentifiersOnly' when you only need to list or reference tables
• Use 'identifiersOnly' when you need to work with field or view references
• Only use 'full' when you need field types, descriptions, or other detailed configuration

If you only need detailed information on a few tables in a base with many complex tables, it might be more efficient for you to use list_tables with tableIdentifiersOnly, then describe_table with full on the specific tables you want.

This tool is read-only. It does not modify its environment.

⁠Tool: get_record

Get a specific record by ID

This tool is read-only. It does not modify its environment.

⁠Tool: list_bases

List all accessible Airtable bases

⁠Tool: list_comments

List comments on a record

This tool is read-only. It does not modify its environment.

⁠Tool: list_records

List records from a table

This tool is read-only. It does not modify its environment.

⁠Tool: list_tables

List all tables in a specific base

• tableIdentifiersOnly: table IDs and names
• identifiersOnly: table, field, and view IDs and names
• full: complete details including field types, descriptions, and configurations

Note for LLMs: To optimize context window usage, request the minimum detail level needed:

• Use 'tableIdentifiersOnly' when you only need to list or reference tables
• Use 'identifiersOnly' when you need to work with field or view references
• Only use 'full' when you need field types, descriptions, or other detailed configuration

If you only need detailed information on a few tables in a base with many complex tables, it might be more efficient for you to use list_tables with tableIdentifiersOnly, then describe_table with full on the specific tables you want.

This tool is read-only. It does not modify its environment.

⁠Tool: search_records

Search for records containing specific text

This tool is read-only. It does not modify its environment.

⁠Tool: update_field

Update a field's name or description

This tool may perform destructive updates.

⁠Tool: update_records

Update up to 10 records in a table

This tool may perform destructive updates.

⁠Tool: update_table

Update a table's name or description

This tool may perform destructive updates.

⁠Tool: upload_attachment

Upload a file directly to an attachment field on an existing record using Airtable's upload API. Supports files up to 5 MB. For larger files, use create_record or update_records with a public URL. The record must already exist.

⁠Use this MCP Server

{
  "mcpServers": {
    "airtable-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "NODE_ENV",
        "-e",
        "AIRTABLE_API_KEY",
        "mcp/airtable-mcp-server"
      ],
      "env": {
        "NODE_ENV": "production",
        "AIRTABLE_API_KEY": "patABC123.def456ghi789jkl012mno345pqr678stu901vwx"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠