What is Mcp Coding Assistant

MCP-coding-assistant is an MCP server designed to enhance the capabilities of the Cline coding agent by providing intelligent code suggestions, reducing hallucinations, and integrating project documentation to assist AI coders.

Use cases

Use cases include enhancing coding productivity, reducing errors in code generation, providing quick access to relevant documentation, and assisting developers in understanding and utilizing various technologies effectively.

How to use

To use MCP-coding-assistant, install it via Smithery using the command ‘npx -y @smithery/cli install coding-assistant-server --client cline’, set up your environment variables, and ensure you have the necessary prerequisites like Node.js and OpenAI API Key.

Key features

Key features include context-aware code suggestions, automatic documentation retrieval, technology detection, and integration of multiple documentation sources to enrich the knowledge base.

Where to use

MCP-coding-assistant can be used in software development environments where AI coding assistance is needed, particularly in projects that require documentation integration and technology detection.

Coding Assistant Server

The Coding Assistant Server is an MCP (Model Context Protocol) server that enhances the capabilities of the Cline coding agent. It provides intelligent code suggestions, reduces hallucinations, and documents the knowledge base by leveraging your project’s documentation and detecting the technologies used in your codebase.

Features

• Code Suggestions : Offers context-aware code suggestions based on your code snippets and project documentation.
• Documentation Integration : Loads and vectorizes documentation files from the docs directory or from provided URLs.
• Technology Detection : Automatically detects programming languages, frameworks, and libraries used in your project.
• Automatic Documentation Retrieval : Finds and adds official documentation links for detected technologies to the knowledge base.
• Project Path Automation : Reads the project path from project_path.txt to seamlessly integrate with your current project in Cline.
• Multiple Documentation Sources : Accepts multiple documents and links to enrich the knowledge base.

Installation

Installing via Smithery

To install Coding Assistant Server for Cline automatically via Smithery:

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

Prerequisites

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

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.
   • Add your OpenAI API key:

     OPENAI_API_KEY=your_openai_api_key_here
     

5. Build the Project

   npm run build
   

Usage

Starting the Server

Start the Coding Assistant MCP server:

node build/index.js

Integrating with Cline

1. Update MCP Settings
   • Edit your MCP settings configuration file (e.g., cline_mcp_settings.json) to include the coding assistant server:

     {
       "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 the Project Path
   • Create or update the project_path.txt file in the coding-assistant-server directory with the absolute path to your current project:

     /path/to/your/project
     

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

Using the Tools

get_suggestions Tool

Provides code suggestions based on the provided code context.

Example Usage :

Cline used a tool on the coding-assistant MCP server:

get_suggestions

Get code suggestions based on provided code context

Arguments

{
  "codeContext": {
    "code": "function helloWorld() { console.log('Hello, world!'); }",
    "language": "JavaScript"
  }
}

Response

{
  "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"
    }
  ]
}