Tools
Tables Create
tables_create
MCP
Agent that creates a BigQuery table in the customer's catalog dataset
Create a new table in the project's catalog.
Provide a table name and a list of column definitions (name, type, mode, description).
Playground
Log in
Log in to try this tool. The request uses your session.
Credits
Fixed cost per item requested. Creating a table reads no data, 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
table_name
string
required
Name of the table to create (will be prefixed with the project catalog and must not match a managed table family)
columns
array
required
List of column definitions for the table
Items:
ColumnDefinition
ttl_hours
number | null
Optional time-to-live in hours. If set, the table will be automatically deleted after this duration.
Default: null
Example
{
"table_name": "string",
"columns": [
{
"name": "string",
"type": "STRING",
"mode": "NULLABLE",
"description": null,
"fields": null
}
],
"ttl_hours": null
}
Type Definitions
1 type
These are the available sub-object types that can be used in the
properties above.
ColumnDefinition
object
#
Definition of a column in the table.
name
string
required
Name of the column
type
string
required
BigQuery column type
Values:
STRING
BYTES
INTEGER
INT64
FLOAT
FLOAT64
NUMERIC
BIGNUMERIC
BOOLEAN
BOOL
TIMESTAMP
DATE
TIME
DATETIME
GEOGRAPHY
RECORD
STRUCT
JSON
mode
string
Column mode
Values:
NULLABLE
REQUIRED
REPEATED
Default: "NULLABLE"
description
string | null
Optional description of the column
Default: null
fields
ColumnDefinition
Nested fields for RECORD type columns
Items:
ColumnDefinition
Default: null
Response
object
Properties
table_name
string
required
Name of the created table
created
boolean
required
Whether the table was created
message
string
required
Status message
Example
{
"table_name": "string",
"created": true,
"message": "string"
}
Endpoints
POST
http://agents.botify.com/{organization}/{project}/tables_create/process
POST
http://agents.botify.com/{organization}/{project}/tables_create/batch_process
POST
http://agents.botify.com/{organization}/{project}/tables_create/async_process
POST
http://agents.botify.com/{organization}/{project}/tables_create/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_create/process" \
-H "Authorization: Bearer $BOTIFY_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"item": {
"table_name": "<table_name>",
"columns": []
}
}'
Over MCP
This tool is exposed as the MCP tool tables_create. An MCP client passes
organization, project and item as tool arguments.
Set up MCP →
Raw metadata