create_record
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.
LABSCO SUMMARY
The field schema reaches the model before the model writes a row.
The read path runs spaces, then a node search, then records, with pagination, field filtering and sorting available on the way down. Writing is the part worth having: the schema of the target datasheet goes to the model first, so a new record fills a known structure rather than guessing at column names. Attachments arrive by web URL rather than from local disk, and the storage information that comes back is what gets attached to the row.
What it is
A server over AITable workspaces — spaces, datasheets, forms, dashboards and folders — that reads records out of a datasheet and creates new ones in it.
What you get
- Every workspace the authenticated user can open, plus a node search across datasheets, forms, dashboards and folders by type and query.
- Paginated record reads with field selection, formula filtering and sort order.
- The JSON schema of a datasheet's fields, giving the model the structure a row is expected to have before it writes one.
- Record creation that extracts values from user-provided text and maps them onto that schema.
- Attachment upload from a web URL, returning storage information that a record can be created with.
Requirements
An AITable account with permission on the spaces you want to reach; every tool acts as the currently authenticated user.
Setup effort
One command plus a key — npx -y @apitable/aitable-mcp-server, then supply credentials
USE CASES
01
Getting a model to file a row without inventing column names
The field schema is fetched first and handed to the model, which then pulls the values out of the user's text into a record that matches the datasheet.
02
Tracking down which datasheet holds the numbers
The spaces the account can open are listed, a node search narrows to the datasheets matching a query, and the records come back paginated.
03
Pulling a filtered slice of a datasheet into a report
A formula filter, a field list and a sort order cut the datasheet down to the rows and columns the report needs, one page at a time.
04
Attaching a file that lives on the web to a new row
The attachment is uploaded from its URL and the storage information that comes back is passed straight into the record being created.
6 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
get_fields_schema
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.
list_records
Read the records from a specified datasheet with support for pagination, field filtering, and sorting options.
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. Nodes in AITable can be of several types: datasheets (also known as sheets, or spreadsheets), form, dashboard, and folders.
upload_attachment_via_url
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.
BEFORE YOU INSTALL
What to know first
Tools you get
6 tools when we connected. update_record is documented but marked TODO, so records can be created and given attachments but not edited or deleted.
Requires
- npx on PATH
- AITABLE_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 6 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @apitable/aitable-mcp-serverMCP Clients
Claude Desktop — macOS / Linux
CLAUDE DESKTOP — MACOS / LINUX · JSON
{
"mcpServers": {
"aitable": {
"command": "npx",
"args": [
"-y",
"@apitable/aitable-mcp-server"
],
"env": {
"AITABLE_API_KEY": "<YOUR_AITABLE_API_KEY>"
}
}
}
}Cherry Studio — Windows
CHERRY STUDIO — WINDOWS · JSON
{
"mcpServers": {
"aitable": {
"command": "cmd",
"args": [
"/c",
"npx",
"-y",
"@apitable/aitable-mcp-server"
],
"env": {
"AITABLE_API_KEY": "<YOUR_AITABLE_API_KEY>"
}
}
}
}
