MCP.so
登录

Toolbox - MCP Server Manager

@AlexanderOllman

关于 Toolbox - MCP Server Manager

Agnostic MCP server addition for FastAgent

基本信息

分类

其他

运行时

python

传输方式

stdio

发布者

AlexanderOllman

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "Toolbox": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

工具

未检测到工具

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。

概览

What is Toolbox - MCP Server Manager?

A web application for managing MCP servers and generating configuration files, featuring a FastAPI backend and React frontend. It automatically extracts repository information using GPT, supports YAML and JSON config generation, and provides vector-based search via Qdrant.

How to use Toolbox - MCP Server Manager?

Clone the repository, set up the backend (Python 3.8+, install dependencies, run python run.py on port 8020) and frontend (Node.js 18+, install dependencies, run npm run dev on port 5173). Use CLI tools like add_server.py to add Git repositories or cli.py to generate YAML configs.

Key features of Toolbox - MCP Server Manager

  • Repository management (add, view, delete)
  • Automatic README information extraction via GPT
  • YAML and JSON configuration generation
  • Modern UI with React and Tailwind CSS
  • Command-line tools for repository and config management
  • Vector-based search for repositories

Use cases of Toolbox - MCP Server Manager

  • Centralizing and managing multiple MCP server repositories
  • Automatically generating MCP configuration files from repository metadata
  • Searching through MCP server repositories using semantic similarity
  • Maintaining a local catalog of MCP servers with automatic documentation extraction

FAQ from Toolbox - MCP Server Manager

What are the main dependencies to run Toolbox - MCP Server Manager?

Python 3.8+, Node.js 18+, Git, an OpenAI API key, and a Qdrant vector database instance.

Where is repository data stored and how is it managed?

Repository data is stored in a Qdrant vector database. The connection parameters can be configured in the Vector Settings section of the application.

What CLI tools are available and how do I use them?

Two tools: add_server.py (adds Git repositories to the database) and cli.py (generates YAML configs, lists repositories). Run them from the backend directory with appropriate arguments.

Is the OpenAI API key handled securely?

The README notes that the API key is currently hardcoded in backend/app/services/openai_service.py and recommends using an environment variable in production.

What transports and authentication are used?

The API is served via HTTP on port 8020, with Swagger UI and ReDoc documentation. No authentication mechanism is mentioned in the README.

评论

其他 分类下的更多 MCP 服务器