How does the server interpret natural language?
The server sends the command text to the Google Gemini API, which extracts the intent and parameters (e.g., “add”, “list”, “complete”).
@theatulanand
基本信息
Todo app using mcp server
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"todo-mcp": {
"type": "http",
"url": "http://localhost:3000/sse"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
A simple Todo application enhanced with natural language processing using the Google Gemini API, MongoDB for persistence, and MCP (Model Context Protocol) for real-time updates via Server-Sent Events (SSE). Built with a modular MVC architecture using Express.js, it is intended for developers who want to manage todos through plain‑language commands and receive live updates.
Clone the repository, install dependencies, and create a .env file with PORT, MONGO_URI, and GEMINI_API_KEY. Start the server with npm start. Send POST requests to /api/command with a JSON body containing a "command" field (e.g., {"command": "Add a task to buy milk"}). Supported commands include adding, listing, completing, and deleting todos. Connect to /sse for real‑time updates (requires an MCP‑compatible client).
The server sends the command text to the Google Gemini API, which extracts the intent and parameters (e.g., “add”, “list”, “complete”).
Todos are stored in a MongoDB Atlas (cloud) cluster using Mongoose as the ODM.
Connect to the `/sse` endpoint with an MCP‑compatible client. The server pushes SSE events when todos change.
Node.js v18 or higher, a MongoDB Atlas cluster, and a Google Gemini API key (available from Google AI Studio).
Set `PORT`, `MONGO_URI`, and `GEMINI_API_KEY` in a `.env` file in the project root. The server reads these on startup.
PayPerFax MCP server: send a fax from your AI assistant. Pay per fax, no account.

Employee credential, certification and training tracking for multi-location teams: expiring and overdue credentials, training gaps and location compliance, with owner-controlled write approvals.

Multiplayer coding in the agentic era through an MCP server for real-time codebase sync between your agents.

Spark Inventory’s MCP server lets Claude, ChatGPT and other AI agents work with your inventory. They can check stock, read Demand ESP forecasts (a model per SKU picked by backtest, with stockout correction and seasonalit

Deterministic writing filter. 43 AI patterns marked, each quoting the line that triggered it and attaching the fix. Connects as a remote MCP server at one URL. The free tier runs 3 drafts a day at 12,000 characters, no a
评论