Cold's MCP Server - Project Management System
Enables AI assistants to create, manage, and track projects with associated todos, including CRUD operations and filtering by status, priority, and project.
README
Cold's MCP Server - Project Management System
A powerful MCP (Model Context Protocol) server deployed on Cloudflare Workers that provides project and task management capabilities. This server allows AI assistants to create, manage, and track projects with associated todos through a simple API.
π Features
- Project Management: Create, list, update, and delete projects
- Task Management: Create, organize, and track todos with priorities and due dates
- Cloud-Powered: Built on Cloudflare Workers for global availability
- Persistent Storage: Uses Cloudflare KV for reliable data persistence
- Real-time Sync: Server-Sent Events (SSE) support for real-time updates
- Type-Safe: Full TypeScript implementation with Zod validation
π Available Tools
Project Management
create-project- Create new projects with name and descriptionlist-projects- List all projects with detailsupdate-project- Update project name or descriptiondelete-project- Delete project and all associated todos
Todo Management
create-todo- Create todos with title, priority, and due dateslist-todos- List todos (all or by project)update-todo-status- Update todo status (pending/in-progress/completed)update-todo-priority- Update todo priority (low/medium/high)update-todo-title- Update todo titledelete-todo- Delete specific todos
Advanced Filtering
list-todos-by-status- Filter todos by statuslist-todos-by-priority- Filter todos by prioritylist-todos-by-project-and-status- Filter by project and statuslist-todos-by-project-and-priority- Filter by project and priority
π οΈ Installation & Deployment
Quick Deploy
Local Development
# Clone and setup
npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless
cd my-mcp-server
npm install
# Start development server
npm run dev
# Deploy to production
npm run deploy
π§ Configuration
The server uses Cloudflare KV namespaces for data storage:
PROJECTS_KV- Stores project dataTODOS_KV- Stores todo/task data
Update your wrangler.jsonc:
{
"kv_namespaces": [
{
"binding": "PROJECTS_KV",
"id": "your-namespace-id",
"remote": true
},
{
"binding": "TODOS_KV",
"id": "your-namespace-id",
"remote": true
}
]
}
π Connecting to MCP Clients
Claude Desktop
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"cold-project-manager": {
"command": "npx",
"args": [
"mcp-remote",
"https://your-worker.your-subdomain.workers.dev/sse"
]
}
}
}
Cloudflare AI Playground
- Visit https://playground.ai.cloudflare.com/
- Enter your worker URL:
https://your-worker.your-subdomain.workers.dev/sse - Start managing projects with AI!
π Usage Examples
Creating a Project
// Create a new React project
{
"action": "create-project",
"projectName": "my-react-app",
"projectDescription": "Modern React application with TypeScript"
}
Managing Todos
// Add a high-priority todo
{
"action": "create-todo",
"projectId": "project-uuid",
"todoTitle": "Set up CI/CD pipeline",
"todoPriority": "high"
}
// Update todo status
{
"action": "update-todo-status",
"todoId": "todo-uuid",
"todoStatus": "in-progress"
}
ποΈ Architecture
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
β MCP Client βββββΆβ Cloudflare Worker βββββΆβ KV Storage β
β (Claude/Playground)β β (MCP Server) β β (Projects/Todos)β
βββββββββββββββββββ ββββββββββββββββββββ βββββββββββββββββββ
π― Use Cases
- AI Project Assistants: Help developers manage their coding projects
- Task Automation: Create and track development workflows
- Team Collaboration: Shared project management across teams
- Learning Projects: Organize tutorial and learning project progress
- Freelance Work: Manage client projects and deliverables
π€ Contributing
- Fork the repository
- Create a feature branch
- Add your tools to
src/index.ts - Update storage schemas in
src/storage.ts - Test with
npm run dev - Deploy and submit a PR
π License
MIT License - feel free to use this in your own MCP servers!
π Links
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.