deepview-mcp 0.2.0

A Model Context Protocol server for analyzing large codebases using Gemini 2.0

DeepView MCP

DeepView MCP is a Model Context Protocol server that enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini 2.5 Pro's extensive context window.

Features

• Load an entire codebase from a single text file (e.g., created with tools like repomix)
• Query the codebase using Gemini 2.5 Pro's large context window (up to 2M tokens)
• Connect to IDEs that support the MCP protocol, like Cursor and Windsurf
• Configurable Gemini model selection via command-line arguments

Prerequisites

• Python 3.13+
• Gemini API key from Google AI Studio

Installation

Using pip

pip install deepview-mcp

Using Poetry

poetry add deepview-mcp

From Source

1. Clone the repository:

   git clone https://github.com/ddegtyarev/deepview-mcp.git
   cd deepview-mcp
   

2. Install with Poetry:

   poetry install
   

3. Set up your environment variables:

   cp .env.example .env
   

   Then edit the .env file and add your Gemini API key.

Usage

Starting the Server

Run the server with:

# Basic usage with default settings
deepview-mcp [path/to/codebase.txt]

# Specify a different Gemini model
deepview-mcp [path/to/codebase.txt] --model gemini-2.0-pro

# Change log level
deepview-mcp [path/to/codebase.txt] --log-level DEBUG

The codebase file parameter is optional. If not provided, you'll need to specify it when making queries.

Command-line Options

• --model MODEL: Specify the Gemini model to use (default: gemini-2.5-pro-exp-03-25)
• --log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}: Set the logging level (default: INFO)

Using with an IDE

Cursor

1. Open Cursor's settings
2. Find the MCP section and add a new server
3. Use a config like: {"command": "deepview-mcp", "args": ["path/to/codebase.txt"]}
4. Restart Cursor to connect

Windsurf

1. Open Windsurf's settings
2. Navigate to the MCP configuration
3. Add a new MCP server with the following configuration:

   {
     "mcpServers": {
       "deepview": {
         "command": "/path/to/deepview-mcp",
         "args": ["/path/to/codebase.txt"],
         "env": {
           "GEMINI_API_KEY": "your_gemini_api_key"
         }
       }
     }
   }
   

4. Restart Windsurf to connect

Available Tools

The server provides one tool:

1. deepview: Ask a question about the codebase
   • Required parameter: question - The question to ask about the codebase
   • Optional parameter: codebase_file - Path to a codebase file to load before querying

Preparing Your Codebase

DeepView MCP works best with a single file containing your entire codebase. You can use repomix to prepare your codebase in an AI-friendly format.

Using repomix

1. Basic Usage: Run repomix in your project directory to create a default output file:

# Make sure you're using Node.js 18.17.0 or higher
npx repomix

This will generate a repomix-output.xml file containing your codebase.

2. Custom Configuration: Create a configuration file to customize which files get packaged and the output format:

npx repomix --init

This creates a repomix.config.json file that you can edit to:

• Include/exclude specific files or directories
• Change the output format (XML, JSON, TXT)
• Set the output filename
• Configure other packaging options

3. Loading the Codebase: Use the generated file with DeepView MCP:

deepview-mcp /path/to/repomix-output.xml

Example repomix Configuration

Here's an example repomix.config.json file:

{
  "include": [
    "**/*.py",
    "**/*.js",
    "**/*.ts",
    "**/*.jsx",
    "**/*.tsx"
  ],
  "exclude": [
    "node_modules/**",
    "venv/**",
    "**/__pycache__/**",
    "**/test/**"
  ],
  "output": {
    "format": "xml",
    "filename": "my-codebase.xml"
  }
}

For more information on repomix, visit the repomix GitHub repository.

License

MIT

Author

Dmitry Degtyarev ([e-mail])