Analyzes GitHub repositories by cloning and reading key files to generate documentation.
Uses Gemini AI to perform analysis and generate comprehensive documentation from repository content.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@codeglance-mcp Analyze the GitHub repo https://github.com/tiangolo/fastapi"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that analyzes GitHub repositories using Gemini AI and generates comprehensive documentation — project overviews, architecture guides, file insights, and more.
Works with any MCP-compatible client: Claude Code, Claude Desktop, Cursor, Windsurf, etc.
Get a free API key from Google AI Studio.
claude mcp add codeglance -e GEMINI_API_KEY=your_key_here -- uvx codeglance-mcpThat's it. Verify with:
claude mcp listAdd to your MCP config file (claude_desktop_config.json, .cursor/mcp.json, etc.):
{
"mcpServers": {
"codeglance": {
"command": "uvx",
"args": ["codeglance-mcp"],
"env": {
"GEMINI_API_KEY": "your_gemini_api_key_here"
}
}
}
}pip install codeglance-mcpThen configure your MCP client to run codeglance-mcp as the command instead of uvx codeglance-mcp.
Related MCP server: revibe-mcp
When you ask your AI assistant to analyze a repository, CodeGlance:
Clones the repository (shallow clone for speed)
Reads key files (README, package.json, config files, entry points)
Sends the context to Gemini AI with specialized analysis prompts
Generates 6 documentation files in codeglance-analysis/guide/
File | Description |
| 5-minute project overview |
| Annotated directory structure |
| Key files and their purposes |
| System architecture deep-dive |
| Getting started guide |
| Comprehensive technical analysis |
Tool | Description |
| Run full analysis on a GitHub repo |
| Check if a repo is already cloned |
| List generated documentation files |
Prompt | Description |
| Full analysis workflow |
| Fast overview only |
| Architecture-focused analysis |
| Security-focused review |
All settings can be customized via environment variables in your MCP config:
Variable | Default | Description |
| (required) | Your Google Gemini API key |
|
| Max characters per file to analyze |
|
| Max files to include in analysis |
|
| API request timeout |
|
| Concurrent Gemini API calls |
|
| In-memory cache TTL |
Example with custom settings:
{
"mcpServers": {
"codeglance": {
"command": "uvx",
"args": ["codeglance-mcp"],
"env": {
"GEMINI_API_KEY": "your_key",
"TIMEOUT_SECONDS": "180",
"MAX_CONCURRENT_REQUESTS": "5"
}
}
}
}Python 3.11+
Git (for cloning repositories)
A Gemini API key (free tier works)
git clone https://github.com/lucidopus/codeglance-mcp.git
cd codeglance-mcp
uv sync
# Run locally
GEMINI_API_KEY=your_key uv run codeglance-mcpMIT
Execute comprehensive code analysis workflow on a GitHub repository.
Clones the repository, analyzes it with Gemini AI, and generates 6 documentation
files covering overview, structure, file insights, architecture, quick-start, and
a master analysis.
Args:
repo_url: GitHub repository URL to analyze
working_directory: Directory where to create analysis folder (default: current directory)
Inputs: repo_url (required), working_directory. Returns: success, message, output_files, repository_path, +2 more
Get information about a repository and whether it's already cloned locally.
Args:
repo_url: GitHub repository URL
working_directory: Directory where analysis folder should be located
Inputs: repo_url (required), working_directory. Returns: repo_url, repo_name, local_path, already_cloned, +1 more
List all generated guide files in the codeglance-analysis/guide directory.
Args:
working_directory: Directory where codeglance-analysis folder should be located
Inputs: working_directory. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 3 tools
Each tool has a distinct purpose: analyzing a repository, checking its status, and listing output guides. No overlap in functionality.
All tools use a consistent verb_noun snake_case pattern (analyze_repository, get_repository_info, list_generated_guides) making predictions easy.
Three tools are slightly on the lower end for a code analysis server, but they cover the essential workflow without being excessive. The count is reasonable.
The tools cover the core analysis and listing workflow, but lack retrieval of individual guide content, deletion, or configuration options, which are notable gaps.
An MCP server that gives your AI access to the source code and docs of all public github repos
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Official Duck Framework MCP server for AI-assisted development and project scaffolding.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
