What are the system requirements?
Node.js 18 or later is required.
@nicobailon
Basic information
A command-line tool and MCP server that summarizes code files using Gemini Flash 2.0
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A command-line and MCP server tool that recursively summarizes code files in a given directory using Google Gemini Flash 2.0. It integrates with LLM tools like Claude Desktop, Cursor AI, and Cline, and is designed for developers who want to quickly understand codebases without manual reading.
Install Node.js 18+, clone the repository, install dependencies, configure a GOOGLE_API_KEY environment variable, then use the CLI with npm start -- summarize [directory] or start the MCP server with npm start -- server. The server port (default 24312) can be changed via npm start -- config set --port 8080. Connect LLM tools by setting up a JSON config file or using SSE transport with an API key header.
.gitignore rules.Node.js 18 or later is required.
Include your API key in the `x-api-key` header of all requests (except the `/health` endpoint).
Ensure the MCP server is running (`npm start -- server`), verify the port is correct in your configuration, and check for firewall issues.
Start the MCP server, then create or edit `claude_desktop_config.json` with the correct path to the server binary and your `GOOGLE_API_KEY` environment variable, then restart Claude Desktop.
Yes, it has a default limit of 60 requests per minute per IP address, which can be configured in the server settings.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Comments