ctx: The missing link between your codebase and your LLM. Context as Code (CaC) tool with MCP server inside.
@context-hub
ctx: The missing link between your codebase and your LLM. Context as Code (CaC) tool with MCP server inside. について
CTX: a tool that solves the context management gap when working with LLMs like ChatGPT or Claude. It helps developers organize and automatically collect information from their codebase into structured documents that can be easily shared with AI assistants.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"ctx": {
"command": "ctx",
"args": [
"server",
"-c",
"/path/to/project"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is CTX?
CTX is a single ~20 MB binary with zero dependencies that provides a built-in MCP (Model Context Protocol) server for AI development. It integrates with MCP-compatible clients like Claude Desktop, Cursor, and Cline, giving AI direct access to read, write, search, and modify files across your projects. It is designed for developers who want an AI coding companion with full codebase awareness.
How to use CTX?
Install via curl (Linux/WSL) or PowerShell (Windows), then connect to any MCP client using ctx mcp:config for auto-configuration or manually add the ctx server command to your client’s config. For context generation workflows, run ctx init to create a YAML config and ctx generate to build markdown context documents.
Key features of CTX
- MCP server with powerful filesystem tools (read, write, search, modify)
- Custom tools – turn any terminal command into an AI-triggerable tool
- Multi-project development across microservices
- Smart context generation from files, git diffs, URLs, and more
- Declarative YAML config with JSON Schema support
- Zero dependencies – single ~20 MB binary, no Node.js or Python required
Use cases of CTX
- AI-powered development – AI explores, writes, and modifies code in real time
- Multi-service feature development – AI implements changes across multiple microservices
- Context for code review – generate markdown documents with recent diffs and architecture overviews
- Onboarding – produce a comprehensive project overview for new team members
- Documentation generation – extract API surfaces and let AI generate documentation
FAQ from CTX
What dependencies does CTX require?
CTX is a single ~20 MB binary with zero dependencies. No Node.js, Python, or any runtime is needed.
Which MCP clients are supported?
CTX works with any MCP-compatible client, including Claude Desktop, Cursor, and Cline. It is designed with Claude Desktop in mind and works best with it.
How do I install CTX?
On Linux/WSL run the curl command from the README; on Windows run the PowerShell command. Both auto-download and add the binary to your path.
What transport does CTX use?
CTX uses the standard MCP server transport (stdio) by default. No authentication or network configuration is required.
Where does my data live when using CTX?
All data stays local on your filesystem. CTX directly reads and writes files in your project directories; nothing is sent to an external server.
「開発者ツール」の他のコンテンツ
Huoshan Test
volcengineGolf
golf-mcpProduction-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
Test
x1xhlolFULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sou
Hello World MCP Server (Reference Extension)
anthropicsDesktop Extensions: One-click local MCP server installation in desktop apps
Unity MCP (Server + Plugin)
IvanMurzakAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for fr
コメント