How do I install and set up my-mcp-server?
Run `npm install` then `npm run build` to compile the project. The built server is located at `dist/index.js`.
@distractdiverge
基本情報
A prototype using mcp-framework to build tools for AIs
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": {
"my-mcp-server": {
"command": "node",
"args": [
"/absolute/path/to/my-mcp-server/dist/index.js"
]
}
}
}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。
my-mcp-server is a Model Context Protocol (MCP) server built with the mcp-framework, designed to be extended with custom tools. It serves as a template for developers creating MCP-compatible servers that integrate with AI assistants like Claude Desktop.
Install dependencies with npm install, build with npm run build, then configure the server in your Claude Desktop client by adding the appropriate JSON configuration. For local development, point to the built dist/index.js; after publishing to npm, use npx my-mcp-server.
mcp add tool)Run `npm install` then `npm run build` to compile the project. The built server is located at `dist/index.js`.
Use the CLI command `mcp add tool <tool-name>` (e.g., `mcp add tool data-processor`). The project provides an example tool in `src/tools/ExampleTool.ts` as a reference.
Add the server configuration to your Claude Desktop config file (MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`, Windows: `%APPDATA%/Claude/claude_desktop_config.json`). For local development use `"command": "node", "args":["/absolute/path/to/my-mcp-server/dist/index.js"]`; after publishing, use `"command": "npx", "args": ["my-mcp-server"]`.
Update `package.json` with a unique name, version, description, and ensure the `bin` field is correct. Build locally with `npm run build`, login to npm with `npm login`, then run `npm publish`.
Node.js is required. The project uses npm for package management and `mcp-framework` as its core dependency.

Agent-Native Terminal
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

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a
MeroFoundry is a remote MCP server available at https://platform.merofoundry.com/mcp.
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
コメント