About mcp_auto_builder
mcp_auto_builder is a Python library for developers who want to generate, test, and deploy MCP servers from a description through a UI or CLI. It supports development and production modes and can configure Claude Desktop automatically.
Key features
- 01Unified UI and CLI
- 02Generate MCP servers from descriptions
- 03Build and deploy servers
- 04Development and production modes
- 05Automatic Claude Desktop configuration
Use cases
- 01Generate an MCP server from a description
- 02Switch between development and production modes
- 03Configure a server for Claude Desktop
MCP support
The library generates and deploys MCP servers from a description and API key, locally or remotely.
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 READMEmcp_auto_builder
Introduction
Welcome to mcp_auto_builder, the final unified interface designed for global users to effortlessly build, test, and deploy MCP servers locally or remotely. By providing a simple input of your server description and API key (Claude/OpenAI/Grok), this library handles the entire process through its internal libraries, ensuring seamless configuration and deployment.
Features
- Unified UI/CLI Interface: Enjoy a consistent experience whether you prefer a graphical user interface or command-line interaction.
- Single Input Requirement: Simplify your setup by providing just your server description and API key.
- Automatic Generation: Leverage our internal libraries to automatically generate the MCP server tailored to your needs.
- Claude Desktop Auto-Configuration: Streamline the setup of Claude Desktop environments for a smoother user experience.
- Production & Dev Modes: Switch between production-ready deployments and development environments with ease.
Installation Instructions
Prerequisites
Ensure you have Python 3.8 or higher installed on your system.
Using pip
You can install mcp_auto_builder directly from PyPI using the following command:
pip install mcp-auto-builder
From Source
Clone this repository and install manually:
git clone https://github.com/your-repo/mcp_auto_builder.git
cd mcp_auto_builder
pip install -e .
Usage Examples
CLI Example
To use the command-line interface, simply run:
mcp-auto-builder --description "Your server description here" --api-key YOUR_API_KEY
Python Code Example
For those preferring a programmatic approach, you can integrate mcp_auto_builder in your scripts like so:
from mcp_auto_builder import MCPBuilder
# Initialize the builder with your API key and server description
builder = MCPBuilder(api_key='YOUR_API_KEY', server_description='Your server description here')
# Build the server (default mode: production)
builder.build()
# To switch to development mode:
builder.set_mode('dev')
builder.build()
API Documentation
Class: MCPBuilder
Initialization
MCPBuilder(api_key, server_description, mode='production')
- api_key (str): Your API key for Claude/OpenAI/Grok.
- server_description (str): Description of the server you want to build.
- mode (str, optional): Deployment mode ('production' or 'dev'). Defaults to 'production'.
Methods
-
build()- Purpose: Generates and deploys the MCP server based on the provided description and API key.
- Returns: None
-
set_mode(mode)- Purpose: Sets the deployment mode ('production' or 'dev').
- Parameters:
- mode (str): The desired deployment mode.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Feel free to contribute to and modify mcp_auto_builder as per the terms of the MIT License! For any issues or feature requests, please open an issue on our GitHub repository.
⚠️ Development Status
This library is currently in early development. Some tests may be failing with the following issues:
Contributions to fix these issues are welcome! Please submit a pull request if you have a solution.
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.