Skip to main content
Glama
Sign In

Airtable MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted Airtable MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/airtable-mcp-server
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A3.7/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data both describe themselves as the final Step 3 Airtable operation and both operate under the same read-only constraint, making it unclear when an agent should choose one over the other. query_contexts and prompts_menu are more distinct, but the overlap between the two primary action tools significantly harms tool selection.

Naming Consistency3/5

All names use snake_case, which is consistent, but the pattern is mixed: execute_action, query_contexts, and query_data are verb_noun, while prompts_menu is noun_noun. The naming is readable but not fully predictable.

Tool Count4/5

Four tools is a reasonable count for a focused Airtable integration, and the set is not bloated. However, the near-duplication between execute_action and query_data means not every tool clearly earns its place.

Completeness4/5

For a read-only Airtable integration, the surface covers querying data, executing allowed actions, retrieving account/action context, and accessing prompts. There are minor gaps around explicit schema/table discovery, but the stated read-only workflow is largely covered.

Available Tools

4 tools
execute_actionAirtable Data Execute ActionA
Destructive
Inspect

Execute Airtable action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, gcp_project_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before executing.

Airtable is read-only here (OAuth scope airtable.readonly): only SELECT queries succeed; DDL/DML/scripts are rejected by Google.

Inputs: body (required). Returns: object

prompts_menuAirtable PromptsA
Read-only
Inspect

Access Airtable prompt catalog with 4 operations:

  1. List Public Prompts: • request='menu' - No additional params needed • Returns: All public/system prompts available for Airtable

  2. List Custom Prompts: • request='menu', prompt_type='custom', workspace_id= • Returns: All custom prompts for the specified workspace

  3. Get Public Prompt Details: • request='prompt_details', prompt_id= • Returns: Full text/details of a public prompt

  4. Get Custom Prompt Details: • request='prompt_details', prompt_id=, is_custom=True, workspace_id= • Returns: Full text/details of a custom prompt

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsAirtable Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe Airtable requests.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, gcp_project_id, other source metadata, AND available_actions (all read-only actions you can call).

Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object

query_dataAirtable DataA
Read-only
Inspect

Query Airtable data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, gcp_project_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before querying.

Airtable is read-only here (OAuth scope airtable.readonly): only SELECT queries succeed; DDL/DML/scripts are rejected by Google.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • Effect Airtable MCP Server

      glassBead-tc
      A
      license
      Not graded
      quality
      D
      maintenance
      A production-ready MCP server for Airtable that enables programmatic management of bases, tables, fields, and records through Claude Desktop or other MCP clients using Effect for type-safe and robust API interactions.
      9 npm
      1
      MIT

    • Airtable MCP Server

      felores
      A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that provides tools for programmatically managing Airtable bases, tables, fields, and records through Claude Desktop or other MCP clients.
      12
      362 npm
      75
      MIT

    • Airtable OAuth MCP Server

      onimsha
      A
      license
      A
      quality
      D
      maintenance
      A production-ready Model Context Protocol server that enables AI assistants and applications to interact with Airtable bases through a standardized interface with secure OAuth 2.0 authentication.
      10
      3
      MIT
    Try in Browser
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources