接入你的智能体
從發布者安裝。不是 PlugMCP 端點。
遠端 URL 還是本機指令？ 兩種安裝方式的差異
來自發布者
The privacy-first MCP server that transforms any repository into an AI-ready codebase with semantic search and RAG.
RagCode is a Model Context Protocol (MCP) server that instantly makes your project . It enables AI assistants like , , , and to understand your entire codebase through , bridging the gap between your code and Large Language Models (LLMs).
Privacy-first semantic code navigation MCP server using RAG. Features deep AST multi-language support (Go, PHP/Laravel/WP, JS/TS/React, Python), 100% local LLMs (Ollama), and vector search (Qdrant) for AI IDEs like Antigravity, Cursor, Windsurf, Copilot, and Claude.
Built with the official Model Context Protocol Go SDK, RagCode provides 9 powerful tools to index, search, and analyze code, making it the ultimate solution for AI-ready software development.
No Go, no build tools, no configuration needed. Just Docker.
curl -fsSL https://github.com/doITmagic/rag-code-mcp/releases/latest/download/rag-code-mcp_linux_amd64.tar.gz | tar xz && ./ragcode-installer -ollama=docker -qdrant=docker
# Apple Silicon (M1/M2/M3)
curl -fsSL https://github.com/doITmagic/rag-code-mcp/releases/latest/download/rag-code-mcp_darwin_arm64.tar.gz | tar xz && ./ragcode-installer -ollama=docker -qdrant=docker
# Intel Macs
curl -fsSL https://github.com/doITmagic/rag-code-mcp/releases/latest/download/rag-code-mcp_darwin_amd64.tar.gz | tar xz && ./ragcode-installer -ollama=docker -qdrant=docker
Invoke-WebRequest -Uri "https://github.com/doITmagic/rag-code-mcp/releases/latest/download/rag-code-mcp_windows_amd64.zip" -OutFile "ragcode.zip"; Expand-Archive ragcode.zip -DestinationPath . -Force; .\ragcode-installer.exe -ollama=docker -qdrant=docker
That's it! The installer automatically:
rag-code-mcp binaryphi3:medium, mxbai-embed-large)The auto-update feature is available starting with v1.1.18.
How to Upgrade:
If you are on an older version (< v1.1.18): Your version does not know the update command. You must re-run the installation command (the curl command above) one last time. (Don't worry, your indexes and configuration will be preserved).
If you are on v1.1.18 or newer: Simply run:
rag-code-mcp --update
For new installations:
The update system is built-in. Use the installer once, then simply run rag-code-mcp --update anytime to get the latest features.
Once installed, you don't need to configure anything:
💬 "How does the authentication system work?"
💬 "Find all API endpoints in this codebase"
💬 "Show me the User model and its relationships"
First query triggers background indexing. Subsequent queries are instant.
Your code never leaves your machine. RagCode runs entirely on your local infrastructure:
Perfect for: Enterprise codebases, proprietary projects, security-conscious teams.
RagCode automatically detects and manages multiple workspaces with isolated indexes.
📖 Workspace Detection → - Auto-detection, stable IDs, caching
RagCode works with all major AI-powered IDEs:
We welcome contributions! Here's how you can help:
git clone https://github.com/doITmagic/rag-code-mcp.git
cd rag-code-mcp
go mod download
go run ./cmd/rag-code-mcp
RagCode MCP is open source software licensed under the MIT License.
semantic-code-search rag retrieval-augmented-generation mcp-server model-context-protocol ai-code-assistant vector-search code-navigation ollama qdrant github-copilot cursor-ai windsurf go php laravel python django flask fastapi code-intelligence ast-analysis embeddings llm-tools local-ai privacy-first offline-ai self-hosted on-premise zero-cost no-cloud private-code-search enterprise-ai secure-coding-assistant
Built with ❤️ for developers who want smarter AI code assistants
⭐ Star us on GitHub if RagCode helps your workflow!
Built and maintained by DO IT MAGIC SOFTWARE, custom software and applied AI from Pitești, Romania.
Questions? Open an Issue • Read the Docs • Join Discussions
Privacy-first semantic code navigation MCP server using RAG. Features deep AST multi-language support (Go, PHP/Laravel/WP, JS/TS/React, Python), 100% local LLMs (Ollama), and vector search (Qdrant) fo
總覽
Privacy-first semantic code navigation MCP server using RAG. Features deep AST multi-language support (Go, PHP/Laravel/WP, JS/TS/React, Python), 100% local LLMs (Ollama), and vector search (Qdrant) for AI IDEs like Antigravity, Cursor, Windsurf, Copilot, and Claude.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式，而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Rag Code 透過 stdio 在本機執行。
上次檢查時間：2026-10-28。 Privacy-first semantic code navigation MCP server using RAG. Features deep AST multi-language support (Go, PHP/Laravel/WP, JS/TS/React, Python), 100% local LLMs (Ollama), and vector search (Qdrant) for AI IDEs like Antigravity, Cursor, Windsurf, Copilot, and Claude.