Coding Assistant MCP server

The Coding Assistant Server is an MCP (Model Context Protocol) server that enhances the Cline coding agent by providing intelligent code suggestions and reducing hallucinations. It leverages your project's documentation and automatically detects technologies used in your codebase to deliver context-aware assistance.

Installation Options

Quick Installation via Smithery

The easiest way to install the Coding Assistant Server is through Smithery:

npx -y @smithery/cli install coding-assistant-server --client cline

Manual Installation

Prerequisites

• Node.js v14 or higher
• npm v6 or higher
• OpenAI API Key

Installation Steps

1. Clone the repository:

   git clone [repository-url]
   

2. Navigate to the project directory:

   cd coding-assistant-server
   

3. Install dependencies:

   npm install
   

4. Set up environment variables: Create a .env file in the root directory with your OpenAI API key:

   OPENAI_API_KEY=your_openai_api_key_here
   

5. Build the project:

   npm run build
   

Using the Server

Starting the Server

To launch the server manually:

node build/index.js

Integrating with Cline

1. Configure MCP Settings

Edit your Cline MCP settings configuration file (e.g., cline_mcp_settings.json):

{
  "mcpServers": {
    "coding-assistant": {
      "command": "node",
      "args": ["/path/to/coding-assistant-server/build/index.js"],
      "env": {
        "OPENAI_API_KEY": "your_openai_api_key_here"
      }
    }
  }
}

2. Set Project Path

Create or update the project_path.txt file in the coding-assistant-server directory:

/path/to/your/project

3. Restart Cline

Restart Cline or reload the MCP settings to connect to the coding assistant server.

Using the Code Suggestions Tool

The server provides a get_suggestions tool that offers code recommendations based on your context.

Example Usage

When using Cline, the coding assistant will automatically provide suggestions based on:

• Your current code context
• Project documentation
• Detected technologies in your codebase

The server will return relevant suggestions from your documentation and knowledge base in this format:

{
  "suggestions": [
    {
      "source": "example.txt",
      "content": "# Coding Assistant Documentation\n\nThis is a sample documentation file for the coding assistant server. You can add more documentation files here for the server to use.\n"
    }
  ]
}

Key Features

• Documentation Integration: The server automatically loads documentation files from your project's docs directory or from URLs you provide
• Technology Detection: Identifies programming languages, frameworks, and libraries in your codebase
• Automatic Documentation Retrieval: Finds and adds official documentation links for detected technologies
• Multiple Documentation Sources: Accepts various document formats and links to enhance the knowledge base

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "coding-assistant" '{"command":"node","args":["/path/to/coding-assistant-server/build/index.js"],"env":{"OPENAI_API_KEY":"your_openai_api_key_here"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "coding-assistant": {
            "command": "node",
            "args": [
                "/path/to/coding-assistant-server/build/index.js"
            ],
            "env": {
                "OPENAI_API_KEY": "your_openai_api_key_here"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "coding-assistant": {
            "command": "node",
            "args": [
                "/path/to/coding-assistant-server/build/index.js"
            ],
            "env": {
                "OPENAI_API_KEY": "your_openai_api_key_here"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect