simple-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@simple-MCP show me my system information"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
simple-MCP
一个最小的 MCP (Model Context Protocol) server 示例,通过 stdio 暴露一个查询本机硬件信息的工具。
依赖
Python >= 3.13
Related MCP server: mcpscope
安装
uv sync运行
uv run main.pyserver 以 stdio 传输方式启动,等待 MCP 客户端连接。
工具
get_host_info
无参数,返回结构化的主机信息:
字段 | 类型 | 说明 |
| string | 操作系统名称,如 Darwin / Linux / Windows |
| string | 内核版本号 |
| string | CPU 架构,如 x86_64 / arm64 |
| string | 处理器标识,部分平台可能为空 |
| number | 物理内存总量,单位 GB |
| integer | 逻辑核心数,无法探测时为 -1 |
| string | CPU 型号名称,无法探测时为 Unknown |
返回类型是 pydantic model HostInfo,MCP 会据此生成自描述的 output schema,客户端无需解析字符串。
CPU 型号按平台探测:macOS 用 sysctl machdep.cpu.brand_string,Linux 读 /proc/cpuinfo,Windows 读 PROCESSOR_IDENTIFIER,全部失败时回退到 platform 模块。
客户端配置
{
"mcpServers": {
"hostInfoMcp": {
"command": "uv",
"args": ["--directory", "/path/to/simple-MCP", "run", "main.py"]
}
}
}本地验证
uv run tools.py # 直接打印主机信息 JSONAvailable Tools
1 toolget_host_infoA
获取本机硬件与操作系统信息。
返回 system(系统名)、release(内核版本)、machine(架构)、 processor(处理器标识)、memory_gb(总内存 GB)、 cpu_count(逻辑核心数)、cpu_model(CPU 型号)。
Inputs: no named parameters. Returns: 主机硬件与操作系统信息。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion with other tools. The tool's purpose is clearly defined.
The single tool follows a clear verb_noun pattern (get_host_info), which is consistent and descriptive.
One tool is on the low end, but given the server's name 'simple-MCP', it is reasonable for a focused purpose. However, it is borderline for general utility.
The tool returns comprehensive host hardware and OS information (system, kernel, architecture, processor, memory, CPU), covering the domain well with no obvious gaps.
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that publishes CLI tools on your machine for discoverability by LLMs7 npm1MIT
- FlicenseAqualityDmaintenanceA simple local MCP server that provides greeting and integer addition tools.2-
- FlicenseAqualityDmaintenanceLightweight MCP server that exposes tools for system information and weather lookup, designed for agent integration via stdio.1-
- AlicenseAqualityDmaintenanceA minimal MCP server that provides a single 'hello' tool returning 'Hello, world!'.29 npmMIT