mcpField
M
mcp-server

mcp-server

Local
yigmmk.github.ioDeveloper Tools5Updated 76w ago
RepositoryVisit website

About mcp-server

mcp-server is a project for learning to build MCP servers, with README guidance on Python prerequisites and client configuration. It also mentions search and webpage-reading tools from jina.ai.

Key features

  1. 01Learning-oriented MCP server project
  2. 02Python and uv setup guidance
  3. 03Client configuration examples
  4. 04Mentions jina.ai search and webpage reading

Use cases

  1. 01Learn MCP server configuration
  2. 02Set it up with Claude Desktop
  3. 03Reference Python project launch options
  4. 04Review the stated jina.ai tools

MCP support

This is an MCP server project. Its README shows client configuration examples and describes tools involving jina.ai search and webpage reading.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "yigmmk": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli"
      ]
    }
  }
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server

smithery badge

学习写 mcp server

安装 (cline)

Installing via Smithery

To install mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @yiGmMk/mcp-server --client claude
前置依赖

• Python 3.12 or newer • uv package manager

没有安装uv的,请参考文档uv 安装文档

macos或linux可使用如下命令安装

curl -LsSf https://astral.sh/uv/install.sh | sh

windwos,在powershell下安装

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
配置文件

优先使用下面这种配置方式

{
    "mcpServers": {
        "yiGmMk/mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "/path/to/your/mcp-server",
                "run",
                "main.py"
            ],
            "env": {
                "JINA_API_KEY": "jina_api_key,请从https://jina.ai/reader获取",
                "GOOGLE_AI_STUDIO_KEY": "Google AI Studio api key,请从https://aistudio.google.com/apikey获取",
                "PYTHONIOENCODING": "utf-8"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

或使用venv(增加环境变量配置)

{
    "mcpServers": {
        "yiGmMk/mcp-server": {
            "command": "uv",
            "args": [
                "run",
                "/path/to/your/mcp-server/main.py"
            ],
            "env": {
                "VIRTUAL_ENV": "/path/to/your/mcp-server/.venv",
                "JINA_API_KEY": "jina_api_key,请从https://jina.ai/reader获取",
                "GOOGLE_AI_STUDIO_KEY": "Google AI Studio api key,请从https://aistudio.google.com/apikey获取",
                "PYTHONIOENCODING": "utf-8"
            },
            "disabled": false,
            "autoApprove": []
        }
    }
}

jina.ai

jina.ai提供的各种工具,如搜索,读取网页...

TODO

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.