ClickUp MCP Server
An MCP server that enables AI assistants to manage ClickUp workspaces, tasks, comments, and time entries through natural language, deployable on Google Cloud Run.
README
ClickUp MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to ClickUp's project management capabilities. Deploy on Google Cloud Run for a scalable, serverless solution.
Features
Available Tools
Workspace Management
clickup_list_workspaces- List all workspaces/teamsclickup_list_spaces- List spaces in a workspaceclickup_list_folders- List folders in a spaceclickup_list_lists- List all lists
Task Operations
clickup_create_task- Create new tasksclickup_get_task- Get task detailsclickup_update_task- Update existing tasksclickup_delete_task- Delete tasksclickup_list_tasks- List and filter tasks
Collaboration
clickup_add_comment- Add comments to tasksclickup_get_comments- Get task commentsclickup_get_members- List team members
Project Management
clickup_create_list- Create new listsclickup_add_time_entry- Log time entriesclickup_get_time_entries- Retrieve time tracking data
Prerequisites
- Node.js 20+
- Google Cloud Account with billing enabled
- ClickUp API key (get from ClickUp settings)
- Docker (for containerization)
- Google Cloud CLI (
gcloud)
Local Development
Setup
- Clone the repository and install dependencies:
npm install
- Create a
.envfile:
cp .env.example .env
# Edit .env and add your CLICKUP_API_KEY
- Run in development mode:
npm run dev
- Test the health endpoint:
curl http://localhost:8080/health
Building
npm run build
Google Cloud Deployment
Quick Deploy
- Set environment variables:
export GCP_PROJECT_ID="your-project-id"
export CLICKUP_API_KEY="your-clickup-api-key"
export MCP_API_KEY="optional-mcp-api-key" # For securing the MCP endpoint
- Run the deployment script:
./deploy.sh
The script will:
- Enable required Google Cloud APIs
- Store API keys in Secret Manager
- Build and push Docker image to Container Registry
- Deploy to Cloud Run
- Output the service URL
Manual Deployment
- Build the Docker image:
docker build -t gcr.io/YOUR_PROJECT_ID/mcp-server-clickup .
- Push to Container Registry:
gcloud auth configure-docker
docker push gcr.io/YOUR_PROJECT_ID/mcp-server-clickup
- Create secrets in Secret Manager:
echo -n "your-clickup-api-key" | gcloud secrets create clickup-api-key --data-file=-
echo -n "your-mcp-api-key" | gcloud secrets create mcp-api-key --data-file=-
- Deploy to Cloud Run:
gcloud run deploy mcp-server-clickup \
--image gcr.io/YOUR_PROJECT_ID/mcp-server-clickup \
--region us-central1 \
--platform managed \
--allow-unauthenticated \
--set-secrets=CLICKUP_API_KEY=clickup-api-key:latest,MCP_API_KEY=mcp-api-key:latest
Client Configuration
After deployment, configure your MCP client to connect to the Cloud Run service:
{
"mcpServers": {
"clickup": {
"url": "https://mcp-server-clickup-xxxxx.run.app/mcp/sse",
"apiKey": "your-mcp-api-key"
}
}
}
API Authentication
The server supports two levels of authentication:
- ClickUp API Key (Required): Authenticates with ClickUp's API
- MCP API Key (Optional): Secures the MCP endpoint from unauthorized access
If MCP_API_KEY is set, clients must include it in the Authorization header:
Authorization: Bearer your-mcp-api-key
Architecture
- Transport: HTTP with Server-Sent Events (SSE) for Cloud Run compatibility
- Rate Limiting: Built-in rate limiter respects ClickUp's API limits (100 req/min)
- Error Handling: Comprehensive error handling with meaningful error messages
- Security: API keys stored in Google Secret Manager
- Scalability: Auto-scales on Cloud Run based on demand
CI/CD with Cloud Build
The included cloudbuild.yaml enables automatic deployment on git push:
- Connect your GitHub repository to Cloud Build
- Set up a trigger for your main branch
- Commits will automatically build and deploy
Monitoring
View logs and metrics in Google Cloud Console:
- Cloud Run logs: Shows request logs and application output
- Cloud Monitoring: Track performance metrics
- Error Reporting: Aggregate and analyze errors
Cost Optimization
- Cloud Run charges only when handling requests
- Configure max instances to control costs
- Use Cloud Monitoring to track usage
- Consider setting up budget alerts
Troubleshooting
Common Issues
- Authentication Failed: Verify your ClickUp API key is correct
- Rate Limit Exceeded: The built-in rate limiter should prevent this
- Deployment Fails: Check that all required APIs are enabled
- Connection Timeout: Increase the timeout in Cloud Run configuration
Debug Mode
For local debugging:
NODE_ENV=development npm run dev
Security Best Practices
- Always use Secret Manager for API keys
- Enable MCP_API_KEY for production deployments
- Configure Cloud Armor for DDoS protection (optional)
- Set up VPC Service Controls for additional security
- Regularly rotate API keys
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
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。