Cover image
Try Now
2025-02-25

A lightweight Go application that parses JSON configuration files and executes commands with specified environment variables.

3 years

Works with Finder

1

Github Watches

6

Github Forks

31

Github Stars

MCP Starter

A lightweight Go application that parses JSON configuration files and executes commands with specified environment variables.

Features

  • Parses JSON configuration files
  • Executes commands with environment variables
  • Supports single server configuration
  • Cross-platform (Linux, Windows, macOS)

Installation

Pre-built Binaries

Download the latest release for your platform from the Releases page.

From Source

  1. Ensure you have Go installed (version 1.21 or higher)

  2. Clone the repository:

    git clone https://github.com/daniel-lxs/mcp-starter.git
    cd mcp-starter
    
  3. Build the application:

    go build -o mcp-starter
    

    Windows Users: To prevent terminal windows from appearing when the application is launched, use:

    go build -ldflags "-H=windowsgui" -o mcp-starter.exe
    

Usage

  1. Create a JSON configuration file (e.g., config.json):

    {
      "mcpServers": {
        "MyServer": {
          "command": "my-command",
          "args": ["arg1", "arg2"],
          "env": {
            "MY_ENV_VAR": "value"
          }
        }
      }
    }
    
  2. Prepare the command to add it to Cursor:

    path/to/mcp-starter path/to/config.json
    
  3. Paste the command into the "Add MCP Server dialog: image

Note: Use the full path to the executable and the config file.

Configuration

The JSON configuration file must contain exactly one server definition with the following structure:

{
  "mcpServers": {
    "ServerName": {
      "command": "command-to-execute",
      "args": ["argument1", "argument2"],
      "env": {
        "ENV_VAR_NAME": "value"
      }
    }
  }
}
  • command: The command to execute (required)
  • args: Array of arguments to pass to the command (optional)
  • env: Key-value pairs of environment variables (optional)

Development

Building

To build the application:

go build -o mcp-starter

See Installation section for platform-specific build instructions.

Testing

Run the tests:

go test ./...

Linting

Run the linter:

golangci-lint run

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Windows Users

The Windows executable is not code-signed. To run it:

  1. Right-click the .exe file
  2. Select "Properties"
  3. Check "Unblock" under the General tab
  4. Click "OK"
  5. Run the executable

相关推荐

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • https://reddgr.com
  • Delivers concise Python code and interprets non-English comments

  • 林乔安妮
  • A fashion stylist GPT offering outfit suggestions for various scenarios.

  • 田中 楓太
  • A virtual science instructor for engaging and informative lessons.

  • 1Panel-dev
  • 💬 MaxKB is a ready-to-use AI chatbot that integrates Retrieval-Augmented Generation (RAG) pipelines, supports robust workflows, and provides advanced MCP tool-use capabilities.

  • ShrimpingIt
  • Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx

  • Mintplex-Labs
  • The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

  • GLips
  • MCP server to provide Figma layout information to AI coding agents like Cursor

  • open-webui
  • User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

  • Dhravya
  • Collection of apple-native tools for the model context protocol.

  • patchy631
  • In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

    Reviews

    5 (1)
    Avatar
    user_b1kVMARy
    2025-04-18

    As a dedicated user of the mcp-starter, I must say it is an exceptional tool for kickstarting projects efficiently. Created by daniel-lxs, this tool streamlines the initial setup process, saving valuable time. The integration with GitHub and clear documentation enhance usability for both beginners and experienced developers. Highly recommend checking it out at https://github.com/daniel-lxs/mcp-starter!