DeepView MCP

Name: DeepView MCP
Author: ai-1st

@ai-1st

About 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.

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "deepview-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@ai-1st/deepview-mcp",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is DeepView MCP?

DeepView MCP is a Model Context Protocol server that enables IDEs like Cursor and Windsurf to analyze large codebases using Gemini's large context window. It is designed for developers who want to query entire codebases from within their IDE.

How to use DeepView MCP?

Install via pip (pip install deepview-mcp) or automatically through Smithery. Requires Python 3.13+ and a Gemini API key from Google AI Studio. Configure the server in your IDE's MCP settings with a JSON object specifying the command, optional args (e.g., --model), and environment variable GEMINI_API_KEY. The server exposes one tool, deepview, which accepts a question parameter and an optional codebase_file parameter. Prepare your codebase as a single text file using a tool like repomix.

Key features of DeepView MCP

Load an entire codebase from a single text file.
Query the codebase using Gemini's large context window.
Connect to IDEs supporting MCP, like Cursor and Windsurf.
Configurable Gemini model selection via command-line arguments.

Use cases of DeepView MCP

Ask questions about a large codebase without manual file-by-file searches.
Debug or understand unfamiliar code by querying the full repository from an IDE.
Automate code reviews or documentation generation across an entire project.

FAQ from DeepView MCP

How do I prepare my codebase for DeepView MCP?

Use a tool like repomix to generate a single file (e.g., XML) containing your entire project. You can configure repomix to include/exclude specific file types and directories.

What Gemini models are supported?

You can specify any Gemini model via the --model command-line argument. The default model is gemini-2.0-flash-lite. For example, --model gemini-2.5-pro-exp-03-25.

Do I need to start the DeepView MCP server manually?

No, the server is started automatically by your IDE when you configure it in the MCP settings. You only need to provide the correct command and environment variables.

What tools does DeepView MCP provide?

It provides one tool called deepview which accepts a required question parameter and an optional codebase_file parameter to ask queries about your codebase.

What are the dependencies and runtime requirements?

Python 3.13 or higher and a Gemini API key. The codebase file must be prepared externally (e.g., with repomix). No other external services are required.