What is the default port and endpoint?
The server listens on port 3000 by default (configurable via the `PORT` environment variable), and the JSON-RPC endpoint is at `/rpc`.
@izaqyos
基本情報
This is a simple example server implementing a To-Do list CRUD API using the Model Context Protocol (MCP) concepts, specifically using JSON-RPC 2.0 over HTTP. It uses Node.js, Express, and PostgreSQL (via Docker) for persistence.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"toyMCP": {
"command": "docker",
"args": [
"compose",
"up",
"-d",
"db"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
toyMCP To-Do List Server is a simple example server that implements a To-Do list CRUD API using the Model Context Protocol (MCP) concepts, specifically JSON-RPC 2.0 over HTTP. It uses Node.js, Express, and PostgreSQL (via Docker) for persistence, and includes an AI-powered agent framework for natural language interaction.
Set up prerequisites: Node.js, npm, Docker, and Docker Compose. Clone the repository, run npm install, start PostgreSQL with docker compose up -d db, then start the server with npm start. The JSON-RPC endpoint is at http://localhost:3000/rpc. Authenticate by logging in at /auth/login with username and password to obtain a JWT token, then include it as an Authorization: Bearer <token> header in subsequent requests. Use curl to call methods like todo.list, todo.add, todo.remove, or mcp.discover. For natural language management, use the agent framework in the agent-framework/ directory.
The server listens on port 3000 by default (configurable via the `PORT` environment variable), and the JSON-RPC endpoint is at `/rpc`.
Send a POST request to `/auth/login` with your username and password. Copy the token from the response, then include it as an `Authorization: Bearer <token>` header in all subsequent requests to protected endpoints.
The methods are `todo.list`, `todo.add`, `todo.remove`, and `mcp.discover` (which describes the service and its available methods).
The server requires Node.js, npm, Docker, and Docker Compose for the PostgreSQL database. The agent framework can use local Ollama or OpenAI cloud models.
Use the `clean_start.sh` script, which stops and removes the database container, restarts it, and then starts the server fresh.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Zyte MCP is a remote MCP server available at https://mcp.zyte.com/v1/mcp/, that lets an agent use Zyte on your behalf: to get web pages, to extract data from them, to search the web, and to work with your Scrapy Cloud pr

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
コメント