Project Planner MCP Server
Allows managing projects and todos through the Cloudflare AI Playground.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Project Planner MCP ServerCreate a new project called 'Blog Redesign' and add a todo for wireframes"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Project Planner MCP Server
A remote Model Context Protocol server for lightweight project and todo management, built on Cloudflare Workers and Workers KV. It exposes tools that let any MCP client (Claude Desktop, the Cloudflare AI Playground, etc.) create projects, attach todos to them, and track progress — no authentication required.
Tools
Tool | Description |
| Create a new project ( |
| List all projects |
| Get a project by ID, including its todos |
| Delete a project and all of its todos |
| Create a todo under a project ( |
| Get a single todo by ID |
| Update a todo's title, description, status, or priority |
| Delete a todo by ID |
| List a project's todos, optionally filtered by |
Related MCP server: Todoist MCP Server
Data model
Data is stored in a single KV namespace (PROJECT_PLANNER_STORE):
project:list— array of all project IDsproject:<projectId>— the project objectproject:<projectId>:todos— array of todo IDs belonging to that projecttodo:<todoId>— the todo object
Project structure
remote-mcp-server-authless/
├── src/
│ └── index.ts # MCP server definition (McpAgent + tools)
├── wrangler.jsonc # Worker + KV namespace configuration
├── worker-configuration.d.ts # Generated Env types (wrangler types)
└── tsconfig.jsonSetup
Install dependencies:
npm installCreate a KV namespace (if you don't already have one) and set its id under kv_namespaces in wrangler.jsonc:
npx wrangler kv namespace create PROJECT_PLANNER_STOREDevelopment
Run the server locally:
npm run devThis starts the Worker at http://localhost:8787, with the MCP endpoint at http://localhost:8787/mcp.
Other useful scripts:
npm run type-check # tsc --noEmit
npm run lint:fix # oxlint --fix
npm run format # oxfmt --write .
npm run cf-typegen # regenerate worker-configuration.d.ts from wrangler.jsoncDeploy
npm run deployThis deploys the Worker to https://remote-mcp-server-authless.<your-account>.workers.dev/mcp.
Connecting a client
Cloudflare AI Playground
Enter your server URL (
http://localhost:8787/mcplocally, or your deployed*.workers.dev/mcpURL)The project planner tools become available in the playground
Claude Desktop
Claude Desktop speaks MCP over stdio, so remote servers are bridged via the mcp-remote proxy. In Claude Desktop, go to Settings → Developer → Edit Config, and add:
{
"mcpServers": {
"project-planner": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/mcp"
]
}
}
}Swap in your deployed URL to connect to production instead of localhost. Restart Claude Desktop afterwards to pick up the new server.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ThuongHan/project-planner-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server