Google Docs MCP Server
A powerful Model Context Protocol (MCP) server implementation for seamless Google Docs API integration, enabling AI assistants to create, read, update, and manage Google Docs.
README
Google Docs MCP Server
A powerful Model Context Protocol (MCP) server implementation for seamless Google Docs API integration, enabling AI assistants to create, read, update, and manage Google Docs.
Features
- Create new Google Docs with custom titles and content
- Retrieve document content and metadata
- Update existing documents with new content
- List all accessible documents
- Delete documents
- Export documents to different formats (PDF, plain text, etc.)
- Share documents with specific users
- Search for documents by title or content
- Verify connection and credentials
Prerequisites
- Node.js 18 or higher
- A Google Cloud project with the Google Docs API enabled
- Authentication credentials (API key, service account, or OAuth2)
Installation
-
Clone this repository:
git clone https://github.com/lkm1developer/google-docs-mcp-server.git cd google-docs-mcp-server -
Install dependencies:
npm install -
Create a
.envfile with your Google Cloud credentials:# Required GOOGLE_CLOUD_PROJECT_ID=your-project-id # Choose one authentication method: # Option 1A: Service Account with file path (recommended for production) GOOGLE_APPLICATION_CREDENTIALS=path/to/your-service-account-key.json # Option 1B: Service Account with JSON content directly # Useful for environments where you can't create files GOOGLE_APPLICATION_CREDENTIALS_JSON={"type":"service_account","project_id":"...","private_key":"...","client_email":"..."} # Option 2: API Key (simpler for development) GOOGLE_API_KEY=your-api-key # Option 3: OAuth2 (required for user-specific operations) client_id=your-oauth-client-id client_secret=your-oauth-client-secret refresh_token=your-oauth-refresh-token
Authentication Setup
Service Account Authentication
- Go to the Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Docs API and Google Drive API
- Go to "IAM & Admin" > "Service Accounts"
- Create a new service account
- Grant it the necessary roles (e.g., "Docs API User", "Drive API User")
- Create and download a JSON key for the service account
- Set the path to this JSON file in your
.envfile
OAuth2 Authentication
For operations that require user consent (like creating/editing documents):
- Go to the Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Docs API and Google Drive API
- Go to "APIs & Services" > "Credentials"
- Create OAuth client ID credentials (Web application type)
- Add authorized redirect URIs (e.g., http://localhost:3000/oauth2callback)
- Note your Client ID and Client Secret
- Use the following script to get a refresh token:
// get-refresh-token.js
const { google } = require('googleapis');
const http = require('http');
const url = require('url');
const open = require('open');
const destroyer = require('server-destroy');
async function getRefreshToken() {
const oauth2Client = new google.auth.OAuth2(
'YOUR_CLIENT_ID',
'YOUR_CLIENT_SECRET',
'http://localhost:3000/oauth2callback'
);
const scopes = [
'https://www.googleapis.com/auth/documents',
'https://www.googleapis.com/auth/drive'
];
const authorizeUrl = oauth2Client.generateAuthUrl({
access_type: 'offline',
scope: scopes,
prompt: 'consent'
});
console.log('Opening browser for authorization...');
open(authorizeUrl);
return new Promise((resolve, reject) => {
const server = http.createServer(async (req, res) => {
try {
const queryParams = url.parse(req.url, true).query;
if (queryParams.code) {
res.end('Authentication successful! You can close this window.');
server.destroy();
const { tokens } = await oauth2Client.getToken(queryParams.code);
console.log('\nRefresh Token:', tokens.refresh_token);
console.log('\nAdd this refresh token to your .env file as refresh_token');
resolve(tokens.refresh_token);
}
} catch (e) {
reject(e);
}
}).listen(3000);
destroyer(server);
});
}
getRefreshToken().catch(console.error);
Run this script with:
npm install googleapis open server-destroy
node get-refresh-token.js
Building and Running
-
Build the project:
npm run build -
Test your connection:
npx tsx src/test-connection.ts -
Run the server:
npm startOr with specific credentials:
npm start -- --GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json --GOOGLE_CLOUD_PROJECT_ID=your-project-id # Or with JSON content directly: npm start -- --GOOGLE_APPLICATION_CREDENTIALS_JSON='{"type":"service_account","project_id":"..."}' --GOOGLE_CLOUD_PROJECT_ID=your-project-id -
Run the SSE server with authentication:
npx mcp-proxy-auth node dist/index.js
Implementing Authentication in SSE Server
The SSE server uses the mcp-proxy-auth package for authentication. To implement authentication:
-
Install the package:
npm install mcp-proxy-auth -
Set the
AUTH_SERVER_URLenvironment variable to point to your API key verification endpoint:export AUTH_SERVER_URL=https://your-auth-server.com/verify -
Run the SSE server with authentication:
npx mcp-proxy-auth node dist/index.js -
The SSE URL will be available at:
localhost:8080/sse?apiKey=apikeyReplace
apikeywith your actual API key for authentication.
The mcp-proxy-auth package acts as a proxy that:
- Intercepts requests to your SSE server
- Verifies API keys against your authentication server
- Only allows authenticated requests to reach your SSE endpoint
Docker Support
You can also run the server using Docker:
-
Build the Docker image:
docker build -t google-docs-mcp-server . -
Run the container:
docker run -p 8080:8080 \ -e GOOGLE_CLOUD_PROJECT_ID=your-project-id \ -e GOOGLE_APPLICATION_CREDENTIALS_JSON='{"type":"service_account","project_id":"..."}' \ -e client_id=your-client-id \ -e client_secret=your-client-secret \ -e refresh_token=your-refresh-token \ -e AUTH_SERVER_URL=https://your-auth-server.com/verify \ google-docs-mcp-server
MCP Integration
To use this server with Claude or other MCP-compatible assistants, add it to your MCP settings:
{
"mcpServers": {
"google-docs": {
"command": "node",
"args": ["/path/to/google-docs-mcp-server/dist/index.js"],
"env": {
"GOOGLE_CLOUD_PROJECT_ID": "your-project-id",
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/your-service-account-key.json",
"GOOGLE_APPLICATION_CREDENTIALS_JSON": "{\"type\":\"service_account\",\"project_id\":\"...\"}",
"GOOGLE_API_KEY": "your-api-key",
"client_id": "your-oauth-client-id",
"client_secret": "your-oauth-client-secret",
"refresh_token": "your-oauth-refresh-token"
},
"disabled": false,
"autoApprove": []
}
}
}
Available Tools
| Tool Name | Description | Required Parameters |
|---|---|---|
google_docs_create |
Create a new Google Doc | title, content (optional) |
google_docs_get |
Get a Google Doc by ID | documentId |
google_docs_update |
Update a Google Doc with new content | documentId, content, replaceAll (optional) |
google_docs_list |
List Google Docs accessible to the authenticated user | pageSize (optional), pageToken (optional) |
google_docs_delete |
Delete a Google Doc | documentId |
google_docs_export |
Export a Google Doc to different formats | documentId, mimeType (optional) |
google_docs_share |
Share a Google Doc with specific users | documentId, emailAddress, role (optional) |
google_docs_search |
Search for Google Docs by title or content | query, pageSize (optional), pageToken (optional) |
google_docs_verify_connection |
Verify connection with Google Docs API | None |
Example Usage
Here are some examples of how to use the tools:
Create a new document
{
"name": "google_docs_create",
"arguments": {
"title": "My New Document",
"content": "This is the content of my new document."
}
}
Get a document
{
"name": "google_docs_get",
"arguments": {
"documentId": "1Ax7vsdg3_YhKjkl2P0TZ5XYZ123456"
}
}
Update a document
{
"name": "google_docs_update",
"arguments": {
"documentId": "1Ax7vsdg3_YhKjkl2P0TZ5XYZ123456",
"content": "This is the new content.",
"replaceAll": true
}
}
Search for documents
{
"name": "google_docs_search",
"arguments": {
"query": "meeting notes",
"pageSize": 5
}
}
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。