Google Docs MCP | OAuth 2.0 Google Docs connector for AI agents

Tools your document agent reaches for on Google Docs, scoped per user.

CALL ANY TOOL

Get, create, and update Google Docs, list accessible documents, and share with collaborators.

googledocs_list_comments

List comments

List the comments on a Google Doc, including their replies and resolved status. Comments are managed through the Drive API. Supports pagination.

Parameters

Name

Type

Required

Description

document_id

string

Required

The ID of the Google Doc whose comments to list

include_deleted

boolean

Optional

Whether to include deleted comments. Deleted comments have their content and author stripped. Defaults to false.

page_size

integer

Optional

Maximum number of comments to return per page (1-100, default 20)

page_token

string

Optional

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

schema_version

string

Optional

Optional schema version to use for tool execution

start_modified_time

string

Optional

Only return comments modified after this RFC 3339 timestamp

tool_version

string

Optional

Optional tool version to use for execution

googledocs_create_footer

Create footer

googledocs_list_documents

List documents

googledocs_create_header

Create header

googledocs_update_document

Update document

googledocs_create_comment

Create comment

googledocs_reply_to_comment

Reply to comment

googledocs_create_document

Create document

googledocs_update_document_style

Update document style

googledocs_create_footnote

Create footnote

googledocs_update_paragraph_style

Update paragraph style

googledocs_create_named_range

Create named range

googledocs_update_table_row_style

Update table row style

googledocs_create_paragraph_bullets

Create paragraph bullets

googledocs_update_table_cell_style

Update table cell style

googledocs_insert_text

Insert text

googledocs_update_table_column_properties

Update table column properties

googledocs_insert_table

Insert table

googledocs_copy_document

Copy document

googledocs_insert_person

Insert person

googledocs_read_document

Read document

googledocs_replace_image

Replace image

googledocs_export_document

Export document

googledocs_resolve_comment

Resolve comment

googledocs_accept_suggestion

Accept suggestion

googledocs_reject_suggestion

Reject suggestion

googledocs_apply_text_style

Apply text style

googledocs_insert_rich_link

Insert rich link

googledocs_replace_all_text

Replace all text

googledocs_insert_table_row

Insert table row

Build your Agent

Drop the toolkit in, point it at the user, and your document agent can use Google Docs from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googledocs"], toolNames: ["gdocs_document_get", "gdocs_document_create", "gdocs_document_update"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googledocs"], toolNames: ["gdocs_document_get", "gdocs_document_create", "gdocs_document_update"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["googledocs"], toolNames: ["gdocs_document_get", "gdocs_document_create", "gdocs_document_update"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/googledocs",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start using Google Docs.

Search & recall

Copy the prompt

Copied

Find all documents with [keyword] in the title.

Copy the prompt

Copied

Get the content of [document name].

Copy the prompt

Copied

List all documents updated this week.

Copy the prompt

Copied

Find proposals shared with [email].

Action & creation

Copy the prompt

Copied

Create a new document titled [title].

Copy the prompt

Copied

Add a section to [document]: [text].

Copy the prompt

Copied

Replace all instances of [old text] with [new text] in [document].

Copy the prompt

Copied

Share [document] with [email] as editor.

Reporting & drafts

Copy the prompt

Copied

Summarize the key points of [document].

Copy the prompt

Copied

List all headings in [document].

Copy the prompt

Copied

Compare [doc A] and [doc B] for differences.

Copy the prompt

Copied

Find documents with open comments.

SEE HOW AUTH WORKS

Users authorize Google Docs once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Google Docs

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Google Docs

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Google Docs

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Google Docs

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

Same per-user auth pattern across other document agents and MCP connectors. Working code, live demos, fork what fits.

GTM and RevOps Teams

Deal room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

People Ops and HR teams

Performance review collector

Collects review feedback from Airtable and Google Forms scoped to each manager's direct reports, writes per-employee summaries to Notion, and DMs the manager a Slack digest.

People Ops and HR teams

Offer letter routing agent

Drafts the offer in PandaDoc, blocks on the hiring manager's approval in Slack, then emails the candidate their e-signature link. Every call runs as the recruiter who triggered it, never a shared HR bot.

Support and Ops Teams

Support ticket automation agent

Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Google Docs today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Google Docs as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Google Docs oauth 2.0 stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Google Docs?

Yes. Pass a tool name filter to listScopedTools so the document agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Google Docs.

What happens when a user revokes Google Docs access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent write to docs the user has view-only access to?

No. Write operations require editor access. View-only access blocks all mutations. The agent inherits the exact edit rights the user has on each document.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit