How do I add a new tool?
Use the CLI command `mcp add tool my-tool` from the project's root directory. Example tools include `data-processor`, `api-client`, and `file-handler`.
@ClaytonMatos84
基本情報
概要はまだありません
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": {
"connect-mcp-server": {
"command": "node",
"args": [
"/absolute/path/to/connect-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。
connect-mcp-server is a Model Context Protocol (MCP) server built with mcp-framework. It is designed for developers to create, test, and deploy custom MCP tools that can be integrated with MCP clients such as Claude Desktop.
Install dependencies with npm install, build with npm run build, and then run the server directly or via npx. To use with Claude Desktop, add its configuration to the claude_desktop_config.json file, pointing either to the local built script or the published npm package.
mcp add tool <tool-name>.src/tools/ on startup.npx.Use the CLI command `mcp add tool my-tool` from the project's root directory. Example tools include `data-processor`, `api-client`, and `file-handler`.
Add the server configuration to your Claude Desktop config file. For local development, use the absolute path to `dist/index.js`. After publishing to npm, use `"command": "npx", "args": ["connect-mcp-server"]`.
Update `package.json` with a unique name, version, description, and correct `bin` entry. Run `npm run build`, then `npm publish`. Users can then run it with `npx connect-mcp-server`.
Node.js is required. The project is written in TypeScript and must be built with `npm run build` before use.
Tools are placed in the `src/tools/` directory and are automatically loaded by the server on startup. The entry point is `src/index.ts`.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
不止于 CSS
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
コメント