Google Drive connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Set up the connector

   Register your Google Drive credentials with Scalekit so it handles the token lifecycle. You do this once per environment.

   Dashboard setup steps

   Register your Scalekit environment with the Google Drive connector so Scalekit handles the authentication flow and token lifecycle for you. The connection name you create will be used to identify and invoke the connection programmatically. Then complete the configuration in your application as follows:

   Caution

   Google applications using scopes that permit access to certain user data must complete a verification process.

   1. Set up auth redirects

      • In Scalekit dashboard, go to AgentKit > Connections > Create Connection. Find Google Drive and click Create. Click Use your own credentials and copy the redirect URI. It looks like https://<SCALEKIT_ENVIRONMENT_URL>/sso/v1/oauth/<CONNECTION_ID>/callback.

        

      • Navigate to Google Cloud Console → APIs & Services → Credentials. Select + Create Credentials, then OAuth client ID. Choose Web application from the Application type menu.

        

      • Under Authorized redirect URIs, click + Add URI, paste the redirect URI, and click Create.

        

   2. Enable the Google Drive API

      • In Google Cloud Console, go to APIs & Services → Library. Search for “Google Drive API” and click Enable.

   3. Get client credentials

      • Google provides your Client ID and Client Secret after you create the OAuth client ID in step 1.

   4. Add credentials in Scalekit

      • In Scalekit dashboard, go to AgentKit > Connections and open the connection you created.

      • Enter your credentials:

        • Client ID (from above)
        • Client Secret (from above)
        • Permissions (scopes — see Google API Scopes reference)

        

      • Click Save.

4. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'googledrive'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Google Drive:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'googledrive_search_files',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "googledrive"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Google Drive:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="googledrive_search_files",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Search files, content — Search for files and folders in Google Drive using query filters like name, type, owner, and parent folder
• Get file metadata — Retrieve metadata for a specific file in Google Drive by its file ID

Common workflows

Proxy API call

Node.js

const result = await actions.request({
  connectionName: 'googledrive',
  identifier: 'user_123',
  path: '/drive/v3/files',
  method: 'GET',
});
console.log(result);

Python

result = actions.request(
    connection_name='googledrive',
    identifier='user_123',
    path="/drive/v3/files",
    method="GET"
)
print(result)

Download a file

Download a file from Google Drive by its file ID via the Scalekit proxy.

Python

file_id = "<YOUR_FILE_ID>"   # file ID from Drive (visible in the file's URL)
output_path = "downloaded.pdf"

response = actions.request(
    connection_name='googledrive',
    identifier='user_123',
    path=f"/drive/v3/files/{file_id}",
    method="GET",
    query_params={"alt": "media"},
)

with open(output_path, "wb") as f:
    f.write(response.content)

print(f"Downloaded: {output_path} ({len(response.content):,} bytes)")

Upload a file

Upload a file to Google Drive via the Scalekit proxy. Scalekit injects the OAuth token automatically — your app never handles credentials directly.

Python

import mimetypes

file_path = "report.pdf"
file_name = "report.pdf"

with open(file_path, "rb") as f:
    file_bytes = f.read()

mime_type = mimetypes.guess_type(file_path)[0] or "application/octet-stream"

response = actions.request(
    connection_name='googledrive',
    identifier='user_123',
    path="/upload/drive/v3/files",
    method="POST",
    query_params={"uploadType": "media", "name": file_name},
    form_data=file_bytes,
    headers={"Content-Type": mime_type},
)

file_id = response.json()["id"]
print(f"Uploaded: {file_name} (File ID: {file_id})")

googledrive_get_file_metadata

Retrieve metadata for a specific file in Google Drive by its file ID. Returns name, MIME type, size, creation time, and more.

Name	Type	Required	Description
fields	string	No	Fields to include in the response
file_id	string	Yes	The ID of the file to retrieve metadata for
schema_version	string	No	Optional schema version to use for tool execution
supports_all_drives	boolean	No	Support shared drives
tool_version	string	No	Optional tool version to use for execution

googledrive_search_content

Search inside the content of files stored in Google Drive using full-text search. Finds files where the body text matches the search term.

Name	Type	Required	Description
fields	string	No	Fields to include in the response
mime_type	string	No	Filter results by MIME type
page_size	integer	No	Number of files to return per page
page_token	string	No	Token for the next page of results
schema_version	string	No	Optional schema version to use for tool execution
search_term	string	Yes	Text to search for inside file contents
supports_all_drives	boolean	No	Include shared drives in results
tool_version	string	No	Optional tool version to use for execution

googledrive_search_files

Search for files and folders in Google Drive using query filters like name, type, owner, and parent folder.

Name	Type	Required	Description
fields	string	No	Fields to include in the response
order_by	string	No	Sort order for results
page_size	integer	No	Number of files to return per page
page_token	string	No	Token for the next page of results
query	string	No	Drive search query string
schema_version	string	No	Optional schema version to use for tool execution
supports_all_drives	boolean	No	Include shared drives in results
tool_version	string	No	Optional tool version to use for execution

Execute a tool

Node.js

const result = await actions.executeTool({
  connector: 'googledrive',
  identifier: 'user_123',
  toolName: 'googledrive_get_file_metadata',
  toolInput: {},
});
console.log(result);

Python

result = actions.execute_tool(
    connection_name='googledrive',
    identifier='user_123',
    tool_name='googledrive_get_file_metadata',
    tool_input={},
)
print(result)

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

googledrive_get_file_metadata # Retrieve metadata for a specific file in Google Drive by its file ID. Returns name, MIME type, size, creation time, and more. 5 params ▾

Retrieve metadata for a specific file in Google Drive by its file ID. Returns name, MIME type, size, creation time, and more.

Name Type Required Description

file_id string required The ID of the file to retrieve metadata for

fields string optional Fields to include in the response

schema_version string optional Optional schema version to use for tool execution

supports_all_drives boolean optional Support shared drives

tool_version string optional Optional tool version to use for execution

googledrive_search_content # Search inside the content of files stored in Google Drive using full-text search. Finds files where the body text matches the search term. 8 params ▾

Search inside the content of files stored in Google Drive using full-text search. Finds files where the body text matches the search term.

Name Type Required Description

search_term string required Text to search for inside file contents

fields string optional Fields to include in the response

mime_type string optional Filter results by MIME type

page_size integer optional Number of files to return per page

page_token string optional Token for the next page of results

schema_version string optional Optional schema version to use for tool execution

supports_all_drives boolean optional Include shared drives in results

tool_version string optional Optional tool version to use for execution

googledrive_search_files # Search for files and folders in Google Drive using query filters like name, type, owner, and parent folder. 8 params ▾

Search for files and folders in Google Drive using query filters like name, type, owner, and parent folder.

Name Type Required Description

fields string optional Fields to include in the response

order_by string optional Sort order for results

page_size integer optional Number of files to return per page

page_token string optional Token for the next page of results

query string optional Drive search query string

schema_version string optional Optional schema version to use for tool execution

supports_all_drives boolean optional Include shared drives in results

tool_version string optional Optional tool version to use for execution