What dependencies are required?
Bun is required to install dependencies and run the server. For the Docker option, Docker and Docker Compose must be installed.
@grossomanache
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-boilerplate-grossomanache": {
"command": "bun",
"args": [
"run",
"src/index.ts"
]
}
}
}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。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
mcp-boilerplate is a starter template for building Model Context Protocol (MCP) servers, using Bun as the runtime and TypeScript for type safety. It includes a basic echo tool to demonstrate tool listing, invocation, and error handling, and is designed for quick testing with Claude Desktop.
Install dependencies with bun install, then run the server with bun run src/index.ts. For local development, build with bun run build and point Claude Desktop to the compiled dist/index.js. Alternatively, run via Docker Compose using a TCP/port setup with socat.
Bun is required to install dependencies and run the server. For the Docker option, Docker and Docker Compose must be installed.
Two options are provided: run the server via Docker Compose (TCP) and configure Claude Desktop to use a socat container, or build the project with `bun run build` and point Claude Desktop directly to the compiled JavaScript file.
The server includes an echo tool that repeats a provided message, and supports tool listing and rudimentary error handling (e.g., calling echo without a message).
Run `bun run build` in the project directory. The output will be placed in `dist/index.js`.
No, but the README focuses on testing with Claude Desktop. The server can be run standalone via `bun run src/index.ts` after installing dependencies.

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

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

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C
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
评论