Google Docs MCP Server

@Meerkats-Ai

Repository

Basic information

About Google Docs MCP Server

google-docs-mcp-server

#google-docs #mcp-server #api-integration

Google Docs MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "google-docs-mcp-server-meerkats-ai": {
      "command": "node",
      "args": [
        "get-refresh-token.js"
      ]
    }
  }
}

Google Docs MCP Server tools

Create a new Google Doc

Get a Google Doc by ID

Update a Google Doc with new content

List Google Docs accessible to the authenticated user

Delete a Google Doc

Export a Google Doc to different formats

Share a Google Doc with specific users

Search for Google Docs by title or content

Verify connection with Google Docs API

Overview

What is Google Docs MCP Server?

The Google Docs MCP Server is a Model Context Protocol implementation that provides seamless integration with the Google Docs API. It enables AI assistants to create, read, update, delete, export, share, and search Google Docs using structured tool calls.

How to use Google Docs MCP Server?

Install Node.js 18 or higher, enable the Google Docs and Drive APIs in a Google Cloud project, and authenticate using a service account, API key, or OAuth2. Build the project with npm run build, then start the server with npm start (or via Docker). Add the server to your MCP client configuration with the appropriate environment variables for authentication.

Key features of Google Docs MCP Server

Create new Google Docs with custom titles and content
Retrieve document content and metadata by ID
Update existing documents with new content (optional replace all)
List all accessible documents with pagination
Export documents to PDF, plain text, and other formats
Share documents with specific users with role-based permissions

Use cases of Google Docs MCP Server

An AI assistant creating and managing meeting notes or reports
Automating document generation from structured data or user prompts
Searching for documents by title or content to retrieve relevant information
Programmatically sharing documents with collaborators

Frequently asked questions

What are the prerequisites to run this server?

Node.js 18 or higher, a Google Cloud project with the Google Docs API and Google Drive API enabled, and authentication credentials (service account, API key, or OAuth2).

What authentication methods are supported?

Three methods: service account with a JSON key file (recommended for production), API key (simple for development), and OAuth2 (required for user-specific operations such as creating or editing documents).

How can I run the server with Docker?

Build the Docker image with `docker build -t google-docs-mcp-server .` and run the container with environment variables for your Google Cloud project ID and credentials (e.g., `GOOGLE_APPLICATION_CREDENTIALS_JSON`).

Does the server support authenticated SSE endpoints?

Yes, when using SSE mode, you can enable authentication via the `mcp-proxy-auth` package. Set the `AUTH_SERVER_URL` environment variable and run `npx mcp-proxy-auth node dist/index.js`. The SSE endpoint will then require an `apiKey` query parameter.

What are the document export formats?

The server supports exporting documents to multiple MIME types, including PDF (`application/pdf`) and plain text (`text/plain`), among others.

Comments

More Memory & Knowledge MCP servers

HandbookHub MCP

veryayskiy

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K

agentleFS

One permissioned folder your team and your AI agents both log into.

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from