Toolbox - MCP Server Manager
LocalAbout Toolbox - MCP Server Manager
Toolbox - MCP Server Manager is a web app and CLI for cataloging MCP server repositories and generating configuration files. It is for users who manage server repositories and need searchable records and YAML or JSON configs.
Key features
- 01Add, view, and delete repositories
- 02Extract repository details from README files
- 03Generate YAML and JSON configurations
- 04Search repositories with vectors
- 05Manage repositories and configs via CLI
Use cases
- 01Catalog MCP server Git repositories
- 02Find repositories using vector search
- 03Create YAML or JSON server configuration
- 04List repositories or generate config from the CLI
MCP support
It manages MCP server repositories and generates configuration files for them; it does not describe serving tools to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEToolbox - MCP Server Manager
A web application for managing MCP servers and generating configuration files.
Features
- Repository management (add, view, delete)
- Automatic extraction of information from README files using GPT
- YAML and JSON configuration generation
- Modern UI with React and Tailwind CSS
- Command-line tools for repository management and config generation
- Vector-based search for repositories
Project Structure
The project is divided into two main parts:
- Backend: FastAPI server for API endpoints
- Frontend: React application with Tailwind CSS
Prerequisites
- Python 3.8+
- Node.js 18+
- Git
- OpenAI API key
- Qdrant vector database (for repository storage and search)
Getting Started
Backend Setup
- Navigate to the backend directory:
cd backend
- Create a virtual environment:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Run the FastAPI server:
python run.py
The API will be available at http://localhost:8020.
Frontend Setup
- Navigate to the frontend directory:
cd frontend
- Install dependencies:
npm install
- Start the development server:
npm run dev
The web application will be available at http://localhost:5173.
API Documentation
Once the backend is running, you can access the API documentation at:
- Swagger UI: http://localhost:8020/docs
- ReDoc: http://localhost:8020/redoc
Command-Line Tools
The application includes two command-line tools:
Add Server Tool
This tool allows you to add Git repositories to the database:
python backend/add_server.py https://github.com/username/repo.git
Optional arguments:
--name: Custom name for the repository--description: Custom description for the repository--command: Custom command for running the repository--args: Custom arguments for the command
Configuration Tool
This tool provides functionality to manage the configuration:
python backend/cli.py generate-yaml
Available commands:
generate-yaml: Generate a YAML configuration file-o, --output: Specify the output file path-p, --print: Print the YAML to stdout
list: List all repositories in the database
Development Notes
- The OpenAI API key is hardcoded in
backend/app/services/openai_service.py. In a production environment, this should be replaced with an environment variable. - Repository data is stored in Qdrant vector database. Make sure your Qdrant instance is properly configured and backed up regularly.
- Qdrant connection parameters can be configured in the Vector Settings section of the application.
License
MIT
Comments
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.