Google Docs 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 Docs 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 Docs 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:

   1. Set up auth redirects

      • In Scalekit dashboard, go to AgentKit > Connections > Create Connection. Find Google Docs 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 Docs API

      • In Google Cloud Console, go to APIs & Services → Library. Search for “Google Docs 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 = 'googledocs'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Google Docs:', 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: 'googledocs_list_documents',
     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 = "googledocs"
   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 Docs:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="googledocs_list_documents",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• List documents — List all Google Docs documents in the user’s Drive
• Update document — Update the content of an existing Google Doc using batch update requests
• Read document — Read the complete content and structure of a Google Doc including text, formatting, tables, and metadata
• Create document — Create a new blank Google Doc with an optional title

Common workflows

Proxy API call

Node.js

const result = await actions.request({
  connectionName: 'googledocs',
  identifier: 'user_123',
  path: '/v1/documents/<DOCUMENT_ID>',
  method: 'GET',
});
console.log(result);

Python

result = actions.request(
    connection_name='googledocs',
    identifier='user_123',
    path="/v1/documents/<DOCUMENT_ID>",
    method="GET"
)
print(result)

googledocs_create_document

Create a new blank Google Doc with an optional title. Returns the new document’s ID and metadata.

Name	Type	Required	Description
schema_version	string	No	Optional schema version to use for tool execution
title	string	No	Title of the new document
tool_version	string	No	Optional tool version to use for execution

googledocs_read_document

Read the complete content and structure of a Google Doc including text, formatting, tables, and metadata.

Name	Type	Required	Description
document_id	string	Yes	The ID of the Google Doc to read
schema_version	string	No	Optional schema version to use for tool execution
suggestions_view_mode	string	No	How suggestions are rendered in the response
tool_version	string	No	Optional tool version to use for execution

googledocs_update_document

Update the content of an existing Google Doc using batch update requests. Supports inserting and deleting text, formatting, tables, and other document elements.

Name	Type	Required	Description
document_id	string	Yes	The ID of the Google Doc to update
requests	array<object>	Yes	Array of update requests to apply to the document
schema_version	string	No	Optional schema version to use for tool execution
tool_version	string	No	Optional tool version to use for execution
write_control	object	No	Optional write control for revision management

Execute a tool

Node.js

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

Python

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

Google OAuth consent screen verification

Before you use your own Google OAuth credentials in production, understand what end users see on Google’s consent screen when they authorize a connected account.

Audience type	Consent screen behavior	When to use
Internal	Shows your App Name and logo from Branding settings	Only users in your Google Workspace or Cloud Identity organization can authorize the connector
External	Shows {env_name}.scalekit.dev until Google verifies your app	Any user with a Google account can authorize the connector

Why External is required for most AgentKit connectors:

• Internal restricts authorization to users in your Google Workspace or Cloud Identity organization. Users with @gmail.com or other Google accounts outside your organization cannot complete OAuth.
• External is required when end users outside your organization authorize tool access through connected accounts.
• Organization-managed OAuth clients follow the same rules as personal or developer OAuth clients. Switching to an org-owned client does not bypass Google verification.
• Until Google completes verification of your External app, users see scalekit.dev on the consent screen. After verification, your App Name and logo appear.

Separate from Scalekit domain verification

This is Google’s OAuth consent screen behavior—not Scalekit’s. Custom domain controls your Scalekit environment URL for MCP auth branding. It does not replace Google’s app verification for OAuth consent screens.

During development:

• Add Test users under APIs & Services → OAuth consent screen while publishing status is Testing.
• On unverified apps, users can click Advanced → Go to app (unsafe) to proceed during testing.
• Google Workspace admins may need to allowlist your OAuth client.

For Google’s verification requirements and timeline, refer to Google’s OAuth consent screen verification guide.

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.

googledocs_create_document#Create a new blank Google Doc with an optional title. Returns the new document's ID and metadata.3 params▾

Create a new blank Google Doc with an optional title. Returns the new document's ID and metadata.

NameTypeRequiredDescription

schema_versionstringoptionalOptional schema version to use for tool execution

titlestringoptionalTitle of the new document

tool_versionstringoptionalOptional tool version to use for execution

googledocs_list_documents#List all Google Docs documents in the user's Drive. Optionally search by document name. Returns document IDs, names, and metadata with pagination support.4 params▾

List all Google Docs documents in the user's Drive. Optionally search by document name. Returns document IDs, names, and metadata with pagination support.

NameTypeRequiredDescription

order_bystringoptionalSort order for results. Examples: modifiedTime desc, name asc, createdTime desc

page_sizeintegeroptionalNumber of documents to return per page (max 1000, default 100)

page_tokenstringoptionalToken for retrieving the next page of results. Use the nextPageToken from a previous response.

querystringoptionalDrive search query to filter documents. Defaults to all Google Docs. To search by name, use: mimeType = 'application/vnd.google-apps.document' and trashed = false and name contains 'report'

googledocs_read_document#Read the complete content and structure of a Google Doc including text, formatting, tables, and metadata.4 params▾

Read the complete content and structure of a Google Doc including text, formatting, tables, and metadata.

NameTypeRequiredDescription

document_idstringrequiredThe ID of the Google Doc to read

schema_versionstringoptionalOptional schema version to use for tool execution

suggestions_view_modestringoptionalHow suggestions are rendered in the response

tool_versionstringoptionalOptional tool version to use for execution

googledocs_update_document#Update the content of an existing Google Doc using batch update requests. Supports inserting and deleting text, formatting, tables, and other document elements.5 params▾

Update the content of an existing Google Doc using batch update requests. Supports inserting and deleting text, formatting, tables, and other document elements.

NameTypeRequiredDescription

document_idstringrequiredThe ID of the Google Doc to update

requestsarrayrequiredArray of update requests to apply to the document

schema_versionstringoptionalOptional schema version to use for tool execution

tool_versionstringoptionalOptional tool version to use for execution

write_controlobjectoptionalOptional write control for revision management