Google Docs

Provides tab-aware Google Docs access, enabling tab-level read/write, markdown export, and batch updates through MCP.

python

4

GitHub Stars

python

Language

3 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gigabrainobserver-google-docs-mcp-server": {
      "command": "uvx",
      "args": [
        "google-docs-mcp-server"
      ],
      "env": {
        "SUBJECT_EMAIL": "user@domain.com",
        "SERVICE_ACCOUNT_PATH": "/path/to/key.json"
      }
    }
  }
}

You can connect to Google Docs with full tab support using this MCP server, enabling you to read, modify, and manage documents with precise tab handling and markdown-friendly output within your MCP workflows.

How to use

You will run this MCP server alongside your MCP client and invoke its tools to interact with Google Docs. Use the available tools to inspect documents, read content as markdown, create new documents, and apply changes across tabs with batch updates. Tools that target specific tabs accept either tab_id or tab_title (case-insensitive). When using batch operations, the server automatically injects tab identifiers so you can focus on content changes.

How to install

Install Python dependencies and run the server locally in development or production.

pip install google-docs-mcp-server

uvx google-docs-mcp-server

Configuration and usage notes

You will configure the MCP client to point at this server and supply the required credentials for Google APIs.

Two environment variables are required to authenticate and impersonate a Workspace user: SERVICE_ACCOUNT_PATH and SUBJECT_EMAIL.

Environment variables

Variable	Description
`SERVICE_ACCOUNT_PATH`	Path to the service account JSON key file
`SUBJECT_EMAIL`	Email of the Workspace user to impersonate

Setup

Follow these steps to enable Google Docs and Drive access and prepare a service account for domain-wide delegation.

Prerequisites

Python 3.11+
A Google Cloud service account with domain-wide delegation

Install prerequisites and run the server

You must create a Google Cloud project, enable APIs, create a service account, and provide a JSON key. Then start the MCP server with the required environment variables.

MCP client configuration

Add the MCP server entry to your MCP client configuration using the provided command and environment variables.

Example MCP client configuration

{
  "mcpServers": {
    "google-docs": {
      "command": "uvx",
      "args": ["google-docs-mcp-server"],
      "env": {
        "SERVICE_ACCOUNT_PATH": "/path/to/your-service-account-key.json",
        "SUBJECT_EMAIL": "you@yourdomain.com"
      }
    }
  }
}

Environment variables

Variable	Required	Description
`SERVICE_ACCOUNT_PATH`	Yes	Path to the service account JSON key file
`SUBJECT_EMAIL`	Yes	Email of the Workspace user to impersonate

Available tools

list_tabs

List all tabs (including nested) in a document

read_document

Read one tab or all tabs as markdown with proper heading levels

get_document_info

Provide lightweight metadata: title, ID, link, tab list

create_document

Create a new document with optional initial text

append_text

Append text to the end of a specific tab

insert_text

Insert text at a specific character index in a tab

replace_text

Find and replace within a tab or the entire document

batch_update

Perform full batchUpdate operations for formatting, tables, images, and styles

list_documents

Search Drive for documents by name