Ruoyi AI
面向企业级市场的一站式AI应用开发框架，支持多厂商大模型统一接入与管理，具备安全可控的企业知识库与高精度检索优化能力，提供可视化流程编排、自主决策智能体与多智能体协同调度，兼容主流 Agent Skill 协议，帮助企业与开发者零门槛快速构建安全、高效、可落地的AI智能体应用与行业解决方案。
What is Ruoyi AI?
Ruoyi AI is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 面向企业级市场的一站式ai应用开发框架，支持多厂商大模型统一接入与管理，具备安全可控的企业知识库与高精度检索优化能力，提供可视化流程编排、自主决策智能体与多智能体协同调度，兼容主流 agent skill 协议，帮助企业与开发者零门槛快速构建安全、高效、可落地的ai智能体应用与行业解决方案。
面向企业级市场的一站式AI应用开发框架，支持多厂商大模型统一接入与管理，具备安全可控的企业知识库与高精度检索优化能力，提供可视化流程编排、自主决策智能体与多智能体协同调度，兼容主流 Agent Skill 协议，帮助企业与开发者零门槛快速构建安全、高效、可落地的AI智能体应用与行业解决方案。
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 面向企业级市场的一站式AI应用开发框架，支持多厂商大模型统一接入与管理，具备安全可控的企业知识库与高精度检索优化能力，提
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx ruoyi-aiConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Ruoyi AI
RuoYi AI is a full-stack, enterprise-grade AI application framework built on Spring Boot 3 and Vue 3 that provides a unified interface for managing multiple large language model providers (OpenAI, DeepSeek, Alibaba, Zhipu, MiniMax). It ships a built-in RAG pipeline backed by Milvus, Weaviate, or Qdrant, along with visual workflow orchestration and a Langchain4j-powered agent framework. Teams use it to rapidly deploy internal AI portals, knowledge bases, and multi-agent pipelines without building the infrastructure layer from scratch.
Prerequisites
- Docker and Docker Compose installed on your server or workstation
- At least 4 GB RAM and 2 CPU cores for the full stack (MySQL, Redis, Weaviate, MinIO, backend, two frontends)
- API keys for at least one supported LLM provider (OpenAI, DeepSeek, Alibaba Cloud, etc.)
- Git to clone the repository
- An MCP-compatible client (Claude Desktop, Claude Code, etc.) if using the MCP integration layer
Clone the repository
Clone the RuoYi AI monorepo to your local machine. The repo contains sub-projects for the backend API, the admin panel, and the user-facing web frontend.
git clone https://github.com/ageerle/ruoyi-ai.git
cd ruoyi-aiStart all services with Docker Compose (one-click)
The recommended path is to run the bundled all-in-one Compose file, which launches MySQL 8, Redis, Weaviate, MinIO, the Spring Boot backend (port 26039), the admin panel (port 25666), and the user frontend (port 25137) in a single command.
docker-compose -f docker-compose-all.yaml up -dLog in to the admin panel
Once all containers are healthy, open the admin panel in your browser. Use the default credentials — change the password immediately in a production environment.
# Open: http://localhost:25666
# Default credentials: admin / admin123Configure your LLM provider(s)
Inside the admin panel, navigate to the Model Management section and add the API key and endpoint for each LLM provider you want to use (OpenAI, DeepSeek, Alibaba, Zhipu, or MiniMax). Each model configuration specifies the provider type, base URL, and API key.
Set up a knowledge base
Create a knowledge base entry in the admin panel, upload documents (PDF, Word, Excel), and RuoYi AI will chunk and embed them into the configured vector store (Weaviate by default on port 28080). The retrieval pipeline uses high-precision RAG to answer queries against your internal documents.
Configure the MCP server in your client
RuoYi AI exposes an MCP-compatible endpoint for tool expansion. Add it to your MCP client configuration to allow your AI assistant to call into the RuoYi AI agent framework.
{
"mcpServers": {
"ruoyi-ai": {
"command": "npx",
"args": ["ruoyi-ai"],
"env": {
"RUOYI_API_BASE": "http://localhost:26039"
}
}
}
}Ruoyi AI Examples
Client configuration
Minimal claude_desktop_config.json snippet for connecting to a locally running RuoYi AI backend.
{
"mcpServers": {
"ruoyi-ai": {
"command": "npx",
"args": ["ruoyi-ai"],
"env": {
"RUOYI_API_BASE": "http://localhost:26039"
}
}
}
}Prompts to try
Sample prompts once your RuoYi AI instance is running and connected.
- "Search the internal knowledge base for our Q3 product roadmap."
- "Use the DeepSeek model to summarize the uploaded compliance documents."
- "Trigger the customer-support workflow agent and pass it this ticket: [ticket text]."
- "List all active LLM model configurations in RuoYi AI."Troubleshooting Ruoyi AI
Containers fail to start due to port conflicts
Check that ports 25666, 25137, 26039, 23306, 26379, 28080, 29000, and 29090 are free. If not, edit docker-compose-all.yaml to remap them, or stop conflicting services before running Compose.
Vector search returns no results after uploading documents
Verify the Weaviate container is healthy (curl http://localhost:28080/v1/meta) and that the embedding model configuration in the admin panel points to a valid provider. Re-trigger ingestion by re-uploading the document.
LLM API calls fail with authentication errors
Double-check the API key and base URL entered for each provider in the admin Model Management page. For OpenAI-compatible endpoints (e.g., DeepSeek), ensure the base URL ends with /v1 and does not include /chat/completions.
Frequently Asked Questions about Ruoyi AI
What is Ruoyi AI?
Ruoyi AI is a Model Context Protocol (MCP) server that 面向企业级市场的一站式ai应用开发框架，支持多厂商大模型统一接入与管理，具备安全可控的企业知识库与高精度检索优化能力，提供可视化流程编排、自主决策智能体与多智能体协同调度，兼容主流 agent skill 协议，帮助企业与开发者零门槛快速构建安全、高效、可落地的ai智能体应用与行业解决方案。 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Ruoyi AI?
Follow the installation instructions on the Ruoyi AI GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Ruoyi AI?
Ruoyi AI works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Ruoyi AI free to use?
Yes, Ruoyi AI is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Ruoyi AI Alternatives — Similar Coding Agents Servers
Looking for alternatives to Ruoyi AI? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Ruoyi AI in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Ruoyi AI?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.