Chat Desktop App MCP Server

Installation

To install and run the Chat MCP Desktop App:

1. Clone the repository from GitHub:

git clone https://github.com/AI-QL/chat-mcp
cd chat-mcp

2. Ensure Node.js is installed on your system. You can verify this by running:

node -v
npm -v

3. Install dependencies:

npm install

4. Before starting the application, modify the config.json file located in the src/main directory to configure your MCP servers. Ensure that the command and path specified in the args are valid.

5. Start the application:

npm start

Configuration

The application supports various LLM configurations through JSON files. You can create configuration files for different API endpoints:

OpenAI API Configuration

Create a gpt-api.json file with the following content:

{
    "chatbotStore": {
        "apiKey": "",
        "url": "https://api.aiql.com",
        "path": "/v1/chat/completions",
        "model": "gpt-4o-mini",
        "max_tokens_value": "",
        "mcp": true
    },
    "defaultChoiceStore": {
        "model": [
            "gpt-4o-mini",
            "gpt-4o",
            "gpt-4",
            "gpt-4-turbo"
        ]
    }
}

Qwen API Configuration

For Qwen models, create a qwen-api.json file:

{
    "chatbotStore": {
        "apiKey": "",
        "url": "https://dashscope.aliyuncs.com/compatible-mode",
        "path": "/v1/chat/completions",
        "model": "qwen-turbo",
        "max_tokens_value": "",
        "mcp": true
    },
    "defaultChoiceStore": {
        "model": [
            "qwen-turbo",
            "qwen-plus",
            "qwen-max"
        ]
    }
}

DeepInfra Configuration

For DeepInfra models, create a deepinfra.json file:

{
    "chatbotStore": {
        "apiKey": "",
        "url": "https://api.deepinfra.com",
        "path": "/v1/openai/chat/completions",
        "model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
        "max_tokens_value": "32000",
        "mcp": true
    },
    "defaultChoiceStore": {
        "model": [
            "meta-llama/Meta-Llama-3.1-70B-Instruct",
            "meta-llama/Meta-Llama-3.1-405B-Instruct",
            "meta-llama/Meta-Llama-3.1-8B-Instruct"
        ]
    }
}

Building the Application

To build a standalone desktop application:

npm run build-app

This will package your application for your current operating system, with artifacts stored in the /artifacts directory.

For Debian/Ubuntu users experiencing RPM build issues, either:

• Edit package.json to skip the RPM build step, or
• Install RPM: sudo apt-get install rpm

Troubleshooting

Error: spawn npx ENOENT

If you encounter this error, modify the config.json in src/main. On Windows, npx may not work properly. You can use node directly in config.json:

{
    "mcpServers": {
        "filesystem": {
            "command": "node",
            "args": [
                "node_modules/@modelcontextprotocol/server-filesystem/dist/index.js",
                "D:/Github/mcp-test"
            ]
        }
    }
}

Always use absolute paths for better reliability.

Installation Timeout

If the installation process stalls at less than 300MB, it's likely due to a timeout during the Electron installation. This often happens because the download speed from Electron's default server is slow or inaccessible in certain regions. To resolve this, modify the environment or global variable ELECTRON_MIRROR to use an accessible Electron mirror site.

Electron Builder Timeout

When packaging with electron-builder, it downloads several large release packages from GitHub. If your network connection is unstable, this process may timeout. On Windows, clear the cache in the electron and electron-builder directories within C:\Users\YOURUSERNAME\AppData\Local before retrying. Use the default shell terminal instead of VSCode's built-in terminal to avoid permission issues.