About
MCP (Model Context Protocol) integration for rucora
README
用 Rust 编写的高性能、类型安全的 LLM 应用开发框架
crate Documentation License star
✨ 特性
- ⚡ 极速性能 - Rust 原生,零成本抽象
- 🔒 类型安全 - 编译时错误检查,运行时更可靠
- 💰 成本监控 - 内置 Token 计数和成本管理
- 🧰 丰富工具 - 12+ 内置工具(Shell/File/HTTP/Git/Memory 等)
- 🔌 灵活集成 - 支持 10+ LLM Provider(OpenAI、Anthropic、Gemini、Ollama 等)
- 📊 可观测性 - 完整的日志、指标、追踪支持
- 🧠 Agent 架构 - 思考与执行分离,支持自定义 Agent
🚀 快速开始
1. 安装依赖
cargo add rucora
2. 设置环境变量
快速开始示例使用 OpenAiProvider,需要设置以下环境变量:
必需:
OPENAI_API_KEY- OpenAI API 密钥
可选:
OPENAI_BASE_URL- 自定义 API 地址(如使用 Ollama 本地模型或其他兼容服务)
在不同命令行中设置环境变量
Windows CMD:
set OPENAI_API_KEY=sk-your-api-key-here
set OPENAI_BASE_URL=https://api.openai.com/v1
Windows PowerShell:
$env:OPENAI_API_KEY = "sk-your-api-key-here"
$env:OPENAI_BASE_URL = "https://api.openai.com/v1"
Linux / macOS (bash/zsh):
export OPENAI_API_KEY="sk-your-api-key-here"
export OPENAI_BASE_URL="https://api.openai.com/v1"
提示: 以上设置仅对当前终端会话有效。如需永久设置,请将配置添加到你的 shell 配置文件(如
~/.bashrc、~/.zshrc或 PowerShell profile)。
使用 Ollama 本地模型(可选):
# Linux/macOS
export OPENAI_BASE_URL="http://localhost:11434/v1"
# Windows PowerShell
$env:OPENAI_BASE_URL = "http://localhost:11434/v1"
# Windows CMD
set OPENAI_BASE_URL=http://localhost:11434/v1
3. 运行示例代码
use rucora::agent::SimpleAgent;
use rucora::prelude::Agent;
use rucora::provider::OpenAiProvider;
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let provider = OpenAiProvider::from_env()?;
let agent = SimpleAgent::builder(provider)
.model("gpt-4o-mini")
.system_prompt("你是有用的助手")
.build();
let output = agent.run("你好".into()).await?;
println!("{}", output.text().unwrap_or("无回复"));
Ok(())
}
📚 文档
完整文档请查看 docs/README.md
新手入门
技能系统
- Skill 配置规范 - 配置文件完整说明
- Skill 配置示例 - 实际使用示例
架构设计
项目文档
📦 项目结构
rucora/
├── docs/ # 文档目录
│ ├── README.md # 文档导航
│ ├── guides/ # 用户指南(快速开始、用户指南、示例等)
│ ├── design/ # 架构设计文档
│ └── archive/ # 历史存档文档
├── rucora/ # 主库(实现聚合)
├── rucora-core/ # 核心抽象层
├── rucora-providers/ # LLM 提供者实现
├── rucora-tools/ # 工具实现
├── rucora-skills/ # 技能系统
├── rucora-mcp/ # MCP 协议集成
├── rucora-a2a/ # A2A 协议集成
├── rucora-embed/ # 嵌入提供者
├── rucora-retrieval/ # 向量存储实现
└── examples/ # 示例代码
🔧 环境变量
| 变量 | 说明 | 示例 |
|---|---|---|
OPENAI_API_KEY |
OpenAI API 密钥 | sk-... |
OPENAI_BASE_URL |
自定义 API 地址 | http://localhost:11434 |
ANTHROPIC_API_KEY |
Anthropic API 密钥 | sk-ant-... |
GOOGLE_API_KEY |
Google Gemini API 密钥 | ... |
🎯 支持的 Provider
| Provider | 环境变量 | 文档 |
|---|---|---|
| OpenAI | OPENAI_API_KEY |
用户指南 |
| Anthropic | ANTHROPIC_API_KEY |
用户指南 |
| Google Gemini | GOOGLE_API_KEY |
用户指南 |
| Ollama | OPENAI_BASE_URL |
快速开始 |
📝 更新日志
查看 CHANGELOG.md 了解最新版本和变更。
🤝 贡献
欢迎贡献代码、文档或建议!
📄 许可证
rucora 使用 MIT 许可证。
Installing Rucora
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/launcher-rs/rucoraFAQ
Is Rucora MCP free?
Yes, Rucora MCP is free — one-click install via Unyly at no cost.
Does Rucora need an API key?
No, Rucora runs without API keys or environment variables.
Is Rucora hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Rucora in Claude Desktop, Claude Code or Cursor?
Open Rucora on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
GitHub
PRs, issues, code search, CI status
by GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
by mcpdotdirectAmap Maps Mcp Server
MCP server for using the AMap Maps API
by duxiaohuiSupabase
Database, auth and storage
by SupabaseEverything
Reference / test server with prompts, resources, and tools.
Git
Tools to read, search, and manipulate Git repositories.
Sequential Thinking
Dynamic and reflective problem-solving through thought sequences.
Time
Time and timezone conversion capabilities.
Compare Rucora with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All development MCPs
