What is the purpose of this starter kit?
It is a minimal scaffold for creating an MCP server using StdioServerTransport, aimed at simplifying setup and providing example tools.
@akoskm
基本信息
暂无概览
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。
This starter kit provides a simple foundation for creating an MCP (Model Context Protocol) server using the StdioServerTransport. It is intended for developers who want to quickly scaffold a new MCP server that communicates via standard input/output, with example tools and automatic integration with the Cursor editor.
Create a new MCP server by running pnpm dlx github:akoskm/mcp-server-stdio my-mcp-server (PNPM) or npm create @akoskm/mcp-server-stdio my-mcp-server (NPM). This generates a directory with the repository contents. Edit .cursor/mcp.json if you are not using Bun as the runtime. The server is automatically detected by Cursor; restart Cursor if needed.
It is a minimal scaffold for creating an MCP server using StdioServerTransport, aimed at simplifying setup and providing example tools.
Run `pnpm dlx github:akoskm/mcp-server-stdio my-mcp-server` (or the NPM equivalent) to generate a new project directory.
The default runtime is Bun. If you use a different runtime, edit `.cursor/mcp.json` to change the command.
Two tools: `which-app-on-port` (Mac only) returns the command and PID of a process on a given port, and `add two numbers` performs simple addition.
The MCP server is automatically picked up by Cursor after creating the project. If it does not appear, restart Cursor.

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
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
评论