About Google Docs MCP Server
Google Docs MCP Server connects language models to Google Docs for document search and editing. It supports creating documents, appending text, and replacing existing content.
Key features
- 01Search Google Docs with queries
- 02Create documents with initial content
- 03Append content to documents
- 04Replace document content
Use cases
- 01Find documents in Google Drive
- 02Create a document with starter text
- 03Add content to an existing document
- 04Replace the content of a document
MCP support
It exposes Google Docs search and editing operations to MCP clients as tools.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEGoogle Docs MCP Server
A Model Context Protocol (MCP) server for Google Docs API, allowing language models to create, search, append to, and update Google Docs.
Features
- Search Docs: Search for Google Docs in Drive with custom queries
- Create Doc: Create new Google Docs with optional initial content
- Append to Doc: Append content to the end of an existing Google Doc
- Update Doc: Replace content in an existing Google Doc with new content
Setup
Prerequisites
- Node.js (v14 or higher)
- npm
- Google Cloud Platform account with the Google Drive and Google Docs APIs enabled
Installation
-
Clone this repository:
git clone <repository-url> cd google-docs-mcp-server -
Install dependencies:
npm install -
Set up Google API credentials:
- Go to the Google Cloud Console
- Create a new project (or select an existing one)
- Enable the Google Drive API and Google Docs API
- Create OAuth 2.0 credentials (Desktop application)
- Download the credentials JSON file and save it as
credentials.jsonin the project root
-
Get authentication tokens:
node get-refresh-token.jsFollow the browser prompts to authorize the application. This will create a
token.jsonfile. -
Build the server:
npm run build
Building the Extism Plugin
The server uses an Extism WebAssembly plugin to interact with the Google Docs API. To build the plugin:
cd extism-plugin
npm install
npm run build
This will create the plugin.wasm file in the dist directory.
Usage
Running the Server
Start the MCP server:
npm start
Or with explicit node command:
node build/index.js
Testing the Plugin Directly
You can test the Extism plugin directly using the Extism CLI:
cd extism-plugin
extism call --wasi --allow-host www.googleapis.com --allow-host docs.googleapis.com --config GOOGLE_ACCESS_TOKEN=<your-access-token> dist/plugin.wasm describe
To search for docs:
extism call --wasi --allow-host www.googleapis.com --allow-host docs.googleapis.com --config GOOGLE_ACCESS_TOKEN=<your-access-token> dist/plugin.wasm call --input '{"toolId": "search_docs", "arguments": {"query": "name contains \"report\""}}'
To create a new doc:
extism call --wasi --allow-host www.googleapis.com --allow-host docs.googleapis.com --config GOOGLE_ACCESS_TOKEN=<your-access-token> dist/plugin.wasm call --input '{"toolId": "create_doc", "arguments": {"title": "My New Document", "content": "Initial content"}}'
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.