What programming languages does Code Scanner Server support?
It parses JavaScript (`.js`, `.jsx`), TypeScript (`.ts`, `.tsx`), C# (`.cs`), PHP (`.php`), CSS (`.css`), and Python (`.py`) via Tree-sitter.
@Ixe1
基本信息
CLI & MCP server for scanning code definitions (.gitignore aware, LLM output)
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"code-scanner-server": {
"command": "node",
"args": [
"build/index.js",
"--directory",
"/path/to/your/codebase"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Code Scanner Server is a CLI tool and MCP server that scans code files for definitions (classes, functions, etc.), respects .gitignore, provides line numbers, and outputs LLM-friendly formats (XML/Markdown). It is built with TypeScript and Node.js, uses the Tree-sitter parsing library, and is intended for developers who need to extract structural information from codebases programmatically or via AI assistants.
Install dependencies with npm install, then build the TypeScript code with npm run build. Run as a CLI tool by executing node build/index.js --directory /path/to/codebase with optional flags. To use as an MCP server, omit the --directory argument; then add the server to your MCP client configuration (e.g., claude_desktop_config.json) with the absolute path to build/index.js.
It parses JavaScript (`.js`, `.jsx`), TypeScript (`.ts`, `.tsx`), C# (`.cs`), PHP (`.php`), CSS (`.css`), and Python (`.py`) via Tree-sitter.
Add an entry to your MCP client configuration (e.g., `claude_desktop_config.json`) with the command `node` and the absolute path to `build/index.js` as the argument. Then restart your MCP client.
You can choose between Markdown (default), XML, and JSON using the `--format` flag.
The tool is under active development. Core functionality is operational, but some features or language parsers may not be fully tested and might contain bugs or limitations.
You need Node.js and npm installed. The tool is built with TypeScript and requires a build step (`npm run build`) before first use.

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url
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

Build custom POS apps with your AI agent. Final's MCP server lets developers scaffold checkout flows, adapt vetted screen blueprints for counter POS, self-checkout kiosks, restaurant ordering and payment terminals, previ

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
评论