Orcho MCP Server
Provides real-time security risk assessment for AI coding prompts, analyzing potential dangers, blast radius, and complexity before code execution in Cursor.
README
Orcho MCP Server for Cursor
Risk assessment for AI coding prompts - Automatically analyze your coding requests for security and safety risks before execution.
🚀 Quick Install
Click this link to automatically install in Cursor:
cursor://anysphere.cursor-deeplink/mcp/install?name=orcho&config=eyJuYW1lIjoib3JjaG8iLCJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBvcmNob19yaXNrL21jcC1zZXJ2ZXIiXSwiZW52Ijp7Ik9SQ0hPX0FQSV9LRVkiOiJ0ZXN0X2tleV9vcmNob18xMjM0NSJ9fQ==
How to use:
- Copy the link above
- Paste it into your browser's address bar and press Enter
- Cursor will open and automatically configure the MCP server
- Replace the test API key with your real key (see API Configuration)
- Restart Cursor to activate
- Replace the test API key with your real key (see API Configuration)
- Restart Cursor to activate the MCP server
What is Orcho??
Orcho analyzes your coding prompts in real-time to identify potential security risks, dangerous operations, and safety concerns before code is generated or executed.
Features
- 🔍 Real-time Risk Assessment - Analyze prompts using Orcho's risk analysis API
- 📁 Context-Aware - Automatically includes file context for accurate blast radius and complexity analysis
- 🛡️ Security First - Identifies high-risk prompts before execution
- 🔌 Seamless Integration - Works natively with Cursor's Model Context Protocol
Installation
Option 1: One-Click Install (Recommended)
Copy and paste this link into your browser:
cursor://anysphere.cursor-deeplink/mcp/install?name=orcho&config=eyJuYW1lIjoib3JjaG8iLCJ0eXBlIjoic3RkaW8iLCJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBvcmNob19yaXNrL21jcC1zZXJ2ZXIiXSwiZW52Ijp7Ik9SQ0hPX0FQSV9LRVkiOiJ0ZXN0X2tleV9vcmNob18xMjM0NSJ9fQ==
This automatically:
- ✅ Configures the MCP server in Cursor
- ✅ Sets up auto-installation via npx
- ⚠️ Next step: Replace the test API key with your real key (see below)
- ⚠️ Then: Restart Cursor
Option 2: Manual Installation
-
Install the package:
npm install -g @orcho_risk/mcp-server -
Configure Cursor:
Create or edit
~/.cursor/mcp.json(Windows:C:\Users\<YourUsername>\.cursor\mcp.json):{ "mcpServers": { "orcho": { "command": "npx", "args": ["-y", "@orcho_risk/mcp-server"], "env": { "ORCHO_API_KEY": "your-api-key-here" } } } } -
Restart Cursor completely (quit and reopen)
API Configuration
Get Your API Key
- Sign up at app.orcho.ai
- Navigate to API Settings (Dashboard → API Keys)
- Create or copy your API key
- Update your
mcp.jsonfile:- Location:
~/.cursor/mcp.json(orC:\Users\<YourUsername>\.cursor\mcp.jsonon Windows) - Replace
test_key_orcho_12345with your actual API key
- Location:
Test API Key
For initial testing, you can use:
test_key_orcho_12345
Note: The test key has limited functionality and rate limits. Get your own API key from app.orcho.ai for production use.
Security Best Practices
- ✅ Store API keys only in
~/.cursor/mcp.json(not in your project) - ✅ Never commit API keys to version control
- ✅ Rotate keys immediately if accidentally exposed
Usage
Manual Assessment
In Cursor chat, type:
@orcho assess_risk: Your prompt here
Automatic Assessment (Recommended)
Enable automatic risk assessment for all prompts by adding a Cursor rule to your project.
Option 1: Project Rules (Modern - Recommended)
Copy the rule file to your project:
# Create .cursor/rules directory
mkdir -p .cursor/rules
# Copy the rule file
cp node_modules/@orcho_risk/mcp-server/.cursor/rules/orcho-risk-assessment.mdc .cursor/rules/
Or manually copy from:
node_modules/@orcho_risk/mcp-server/.cursor/rules/orcho-risk-assessment.mdc
Option 2: Legacy .cursorrules File
Copy the example rules file:
cp node_modules/@orcho_risk/mcp-server/.cursorrules.example .cursorrules
Note: Project Rules (Option 1) are the modern approach and support more features.
How It Works
Context-Aware Assessment
Orcho automatically gathers context when available:
- Current File: Detects the file open in your editor
- Other Files: Analyzes which files will be modified by the prompt
- Dependency Graph: Optional project dependency information
- Blast Radius: Calculates impact scope of changes
Example
User: "Delete all user data from the database"
→ Cursor calls: @orcho assess_risk with context
→ Risk: HIGH (score: 95)
→ Cursor warns: "⚠️ HIGH RISK: This could cause data loss. Proceed?"
Tool Parameters
task(required): The prompt to assesscurrent_file(recommended): Path to currently open fileother_files(recommended): Array of files that will be modifieddependency_graph(optional): Project dependency graphweights(optional): Custom risk calculation weightsaiignore_file(optional): Path to .aiignore file
Troubleshooting
MCP Server Not Loading
-
Check
mcp.jsonlocation:- Mac/Linux:
~/.cursor/mcp.json - Windows:
C:\Users\<YourUsername>\.cursor\mcp.json
- Mac/Linux:
-
Verify Node.js is installed:
node --version # Requires v18+ -
Check Cursor Developer Tools:
- Help → Toggle Developer Tools
- Look for MCP-related errors in Console
API Errors
- Invalid API Key: Verify the key is correct in
mcp.json - Rate Limits: Check your account quota at app.orcho.ai
- No API Key: The server will use the test key by default (limited functionality)
Still Having Issues?
- Check that Cursor is fully restarted (quit and reopen)
- Verify your API key is valid at app.orcho.ai
- Ensure you have internet connectivity
License
MIT
Support
For issues and questions:
- GitHub Issues: [Your Repo URL]
- Orcho Support: [Support URL]
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。