Agentic Platform
Documentation API reference Tools Skills

Tools

Tables Insert

tables_insert MCP

Agent that inserts data into a BigQuery table in the customer's editable catalog dataset

Insert rows into a table in the project's editable catalog. Only tables created manually by project members can be modified. The table name is specified in the config, and each item contains a single row. Use batch mode to insert multiple rows efficiently.

Playground

Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.

POST
item
row required A single row to insert as a dictionary
config
table_name required Name of the table to insert data into (must be in the editable catalog)

Billing

Fixed cost per item requested. Rows are streamed straight in without reading the table, so no data-scanned charge applies.

These usage SKUs can be charged on a call.

SKU Credits Description
Tool call 1 per request Charged once per successful item.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
row object required

A single row to insert as a dictionary

Example
{
  "row": {}
}

Configuration

object
Properties
table_name string required

Name of the table to insert data into (must be in the editable catalog)

Example
{
  "table_name": "string"
}

Response

object
Properties
table_name string required

Name of the table

rows_inserted integer required

Number of rows inserted

errors array | null required

Any errors that occurred during insertion

Example
{
  "table_name": "string",
  "rows_inserted": 0,
  "errors": [
    {}
  ]
}

Endpoints

POST http://agents.botify.com/{organization}/{project}/tables_insert/process
POST http://agents.botify.com/{organization}/{project}/tables_insert/batch_process
POST http://agents.botify.com/{organization}/{project}/tables_insert/async_process
POST http://agents.botify.com/{organization}/{project}/tables_insert/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/tables_insert/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "row": {}
  },
  "config": {
    "table_name": "<table_name>"
  }
}'

Over MCP

This tool is exposed as the MCP tool tables_insert. An MCP client passes organization, project and item as tool arguments. Set up MCP →

Raw metadata