AITable MCP Server
OfficialThe AITable MCP Server enables LLMs to interact with AITable.ai for data management operations, including:
List Spaces: Fetch all workspaces accessible to the authenticated user
Search Nodes: Retrieve nodes (datasheets, forms, dashboards, folders) based on types, permissions, and queries
List Records: Read records from datasheets with pagination, filtering, and sorting options
Get Fields Schema: Obtain JSON schema of fields to understand data structure
Create Records: Add new records to datasheets with user-provided data
Upload Attachments: Upload files via URLs and associate them with records
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AITable MCP Server list the records from my project tasks database"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AITable MCP Server
A Model Context Protocol server that provides read and write access to AITable.ai. This server enables LLMs to list spaces, search nodes, list records, create records and upload attachments in AITable.ai.
Tools
Tool Name | Availabe | Description |
list_spaces | ✅ | Fetches all workspaces that the currently authenticated user has permission to access. |
search_nodes | ✅ | Retrieve nodes based on specific types, permissions, and queries. |
list_records | ✅ | Read the records from a specified database with support for pagination, field filtering, and sorting options. |
get_fields_schema | ✅ | Returns the JSON schema of all fields within the specified database |
create_record | ✅ | Create a new record in the database. |
upload_attachment_via_url | ✅ | Upload an attachment to the AITable server using its web URL. |
update_record | ❌ | TODO |
Related MCP server: MCP Boilerplate
Environment Variables
AITABLE_API_KEY: Your AITable personal access token.AITABLE_BASE_URL: The base URL of the AITable API. Defaults tohttps://aitable.ai/fusion. You can set it to{YOUR_CUSTOM_BASE_URL}if you are using the APITable(the open-source version of AITable).
Usage
You can use this server in MCP client such as Claude Desktop, CherryStudio, etc.
Claude Desktop
In the case of Claude Desktop, you need to add the following configuration information to the "mcpServers" section of the claude_desktop_config.json file:
For Linux, MacOS:
{
"mcpServers": {
"aitable": {
"command": "npx",
"args": [
"-y",
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/aitable-mcp-server"
],
"env": {
"AITABLE_API_KEY": "YOUR_API_KEY"
}
}
}
}For Windows:
{
"mcpServers": {
"aitable": {
"command": "npx",
"args": [
"-y",
"D:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\aitable-mcp-server"
],
"env": {
"AITABLE_API_KEY": "YOUR_API_KEY"
}
}
}
}Replace YOUR_API_KEY with your AITable personal access token and /ABSOLUTE/PATH/TO/PARENT/FOLDER/aitable-mcp-server with the absolute path to the parent folder of this repository.
CherryStudio If you are using the CherryStudio as MCP client and Windows system, your configuration should look like this:
{
"mcpServers": {
"aitable": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"D:\\ABSOLUTE\\PATH\\TO\\PARENT\\FOLDER\\aitable-mcp-server"
],
"env": {
"AITABLE_API_KEY": "YOUR_API_KEY"
}
}
}
}Debug
The MCP inspector is a developer tool for testing and debugging MCP servers.
To inspect an MCP server implementation, there's no need to clone the MCP inspector repo. Instead, use npx. For example, AITable MCP server is built at dist/index.js. Arguments are passed directly to your server, while environment variables can be set using the -e flag:
npx @modelcontextprotocol/inspector -e AITABLE_API_KEY={YOUR_API_KEY} node build/index.jsThe other way is to clone the MCP inspector repo and connect the AITable MCP server in the inspector interface.
cd path/to/inspector/
npm start -- -e AITABLE_API_KEY={YOUR_API_KEY}Available Tools
6 toolscreate_recordC
Create a new record in the datasheet. Extract key information from user-provided text based on a predefined Fields JSON Schema and create a new record in the datasheet as a JSON object.
Inputs: fields (required), node_id (required), attachments_fields.
get_fields_schemaB
Returns the JSON schema of all fields within the specified database, This schema will be sent to LLM to help the AI understand the expected structure of the data.
Inputs: node_id (required).
list_recordsC
Read the records from a specified datasheet with support for pagination, field filtering, and sorting options.
Inputs: node_id (required), fields, filterByFormula, pageNum, +3 more.
list_spacesB
Fetches all workspaces that the currently authenticated user has permission to access.
search_nodesC
Retrieve nodes based on specific types, permissions, and queries. Nodes in AITable can be of several types: datasheets (also known as sheets, or spreadsheets), form, dashboard, and folders.
Inputs: node_type (required), space_id (required), query.
upload_attachment_via_urlA
Upload an attachment to the AITable server using its web URL. Returns storage information that can be passed to create_record or update_record tools to associate with a specific records.
Inputs: attachment_url (required), node_id (required), attachment_name.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: create_record (create), get_fields_schema (metadata), list_records (read), list_spaces (workspace access), search_nodes (search), and upload_attachment_via_url (attachment handling). The descriptions reinforce unique functions, preventing agent misselection.
All tools follow a consistent verb_noun or verb_noun_preposition pattern (e.g., create_record, get_fields_schema, list_records, list_spaces, search_nodes, upload_attachment_via_url). The naming is uniform and predictable, using snake_case throughout without any deviations.
With 6 tools, this server is well-scoped for managing AITable resources. The count covers essential operations (CRUD-like actions, metadata retrieval, search, and attachment handling) without being overly sparse or bloated, fitting typical server purposes.
The tool set provides strong coverage for core AITable operations, including create, read, search, and attachment management, with clear support for metadata and workspace access. A minor gap exists in update/delete operations for records, which agents might need to work around, but the surface is largely complete for the domain.
Maintenance
Related MCP Connectors
Teable is an AI spreadsheet for business that combines a familiar spreadsheet interface with a structured database. Its remote MCP server lets AI agents inspect project and table structure, read and update records, and access the Teable API through OAuth with existing project permissions. Website: [teable.ai](https://teable.ai)
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that allows AI agents to interact with Apache DolphinScheduler through a standardized protocol, enabling AI-driven workflow management.32Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.10 npm12MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI agents to create, read, and modify Excel workbooks without requiring Microsoft Excel installation.MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides seamless integration with Mingdao platform APIs, enabling AI applications to perform operations like worksheet management, record manipulation, and role management through natural language.38 npmMIT