Google Workspace MCP Server
Provides read/write access to Google Sheets and Google Docs through MCP tools, enabling operations like reading sheets, appending rows, and editing documents.
README
Google Workspace MCP Server
An MCP (Model Context Protocol) server that provides read/write access to Google Sheets and Google Docs.
Available Tools
| Tool | Description |
|---|---|
read_sheet |
Read data from a Google Sheets spreadsheet |
read_doc |
Read text content from a Google Doc |
list_sheets |
List all sheets/tabs in a spreadsheet |
append_to_doc |
Prepend content to a Google Doc |
append_to_sheet |
Append rows to a spreadsheet |
update_sheet |
Update a specific range in a spreadsheet |
Quick Start
1. Install from GitHub
npm install -g github:HarleyCoops/google-workspace-mcp
Or clone and build locally:
git clone https://github.com/HarleyCoops/google-workspace-mcp.git
cd google-workspace-mcp
npm install
npm run build
2. Set Up Google OAuth Credentials
- Go to Google Cloud Console
- Create a new project (or select existing)
- Enable these APIs:
- Google Sheets API
- Google Docs API
- Google Drive API
- Create OAuth 2.0 credentials (Desktop app type)
- Download as
credentials.json
3. Generate OAuth Token
pip install google-auth-oauthlib google-api-python-client
python regenerate_google_token.py
This creates token.json with your OAuth credentials.
4. Configure Your MCP Client
Set the GOOGLE_TOKEN_PATH environment variable to point to your token.json file.
MCP Configuration
Standard JSON Config (Claude Desktop, Cursor, VS Code, etc.)
{
"mcpServers": {
"google-workspace": {
"command": "npx",
"args": ["github:HarleyCoops/google-workspace-mcp"],
"env": {
"GOOGLE_TOKEN_PATH": "/path/to/your/token.json"
}
}
}
}
If installed globally
{
"mcpServers": {
"google-workspace": {
"command": "google-workspace-mcp",
"env": {
"GOOGLE_TOKEN_PATH": "/path/to/your/token.json"
}
}
}
}
If cloned locally
{
"mcpServers": {
"google-workspace": {
"command": "node",
"args": ["/path/to/google-workspace-mcp/build/index.js"],
"env": {
"GOOGLE_TOKEN_PATH": "/path/to/your/token.json"
}
}
}
}
Emergent.sh Setup
For Emergent.sh, you have two options:
Option A: Use as stdio MCP (if supported)
In Emergent's MCP configuration:
{
"command": "npx",
"args": ["github:HarleyCoops/google-workspace-mcp"],
"env": {
"GOOGLE_TOKEN_PATH": "/path/to/token.json"
}
}
Option B: Self-host as HTTP endpoint
If Emergent requires an HTTP/SSE endpoint, you'll need to wrap this server. See the MCP HTTP Transport docs for details.
Environment Variables
| Variable | Description | Default |
|---|---|---|
GOOGLE_TOKEN_PATH |
Path to OAuth token.json | ./token.json |
DAILY_REPO_PATH |
Base path for .env loading | C:\Users\chris\Daily |
Token Generation Script
Save this as regenerate_google_token.py:
from google_auth_oauthlib.flow import InstalledAppFlow
SCOPES = [
'https://www.googleapis.com/auth/drive.readonly',
'https://www.googleapis.com/auth/documents.readonly',
'https://www.googleapis.com/auth/spreadsheets.readonly',
'https://www.googleapis.com/auth/drive.file'
]
def main():
flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
creds = flow.run_local_server(port=0)
with open('token.json', 'w') as f:
f.write(creds.to_json())
print("Token saved to token.json")
if __name__ == '__main__':
main()
Usage Examples
Reading a Sheet
Extract the spreadsheet ID from the URL:
https://docs.google.com/spreadsheets/d/1Zlxn88pgMi0WAKFo.../edit
^^^^^^^^^^^^^^^^
This is the ID
Reading a Doc
Extract the document ID from the URL:
https://docs.google.com/document/d/17p5DfXbyEYhsMy.../edit
^^^^^^^^^^^^^^^
This is the ID
Security Notes
- Never commit
credentials.jsonortoken.jsonto version control token.jsoncontains refresh tokens that provide persistent access- Revoke access anytime at: https://myaccount.google.com/permissions
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。