YUSA MCP Setup & Guide
io.github.yusasecurity/yusa · v0.3.5
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.
Copy the install config on this page first, then verify docs and permissions upstream.
Overview
Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls. YUSA is a MCP Server listed from MCP Registry. Transports: stdio. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.
Use cases
AgentHub Verified AvailabilityTested & Ready
Automated pipeline validated install commands, protocol & client compatibility
Troubleshooting & Common ErrorsFAQ
Common connection errors and verified fixes for YUSA
Getting 'connection closed' or exit code 1 in Cursor / Claude Code for YUSA?
Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.
# Check binary path in terminal: which npx node -v
Getting 'spawn npx ENOENT' or 'command not found'?
The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).
Missing required environment variable or authentication failure?
YUSA requires environment variables (YUSA_POLICY). Ensure you have added valid keys under the 'env' object in your config file without trailing whitespace.
// .cursor/mcp.json 或 claude_desktop_config.json
{
"env": {
"API_KEY": "your_actual_key_here"
}
}Tool Mock Playground
SandboxYUSA Tool Interface Simulation · Preview tool schema & outputs without local runtime
{
"target": "YUSA",
"action": "execute",
"options": {
"mode": "standard",
"timeoutMs": 5000
}
}Click 'Run Mock' above
to preview the raw response returned to the LLM
Decision Guide: Why & When to Use
Assess suitability before installing to save trial-and-error time
- PR review
- Changelog generation
- Cross-repo issue search
- Replacing human security audit
- Unauthorized repo access
YUSA + Scenario Prompt → Complete Agent Automation
MCP hands-on: install to visible results
Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.
Related resources
GitHub
io.mcp-cn.modelcontextprotocol/server-github
连接GitHub的MCP服务器,支持仓库管理、问题跟踪、代码搜索等功能
12306
io.mcp-cn.12306-mcp
12306的MCP服务器,支持12306的读取
MarkItDown MCP Server
io.mcp-cn.markitdown-mcp-npx
MarkItDown MCP服务器,提供无Docker依赖的NPX包装器,支持直接运行Microsoft的markitdown-mcp服务器,包括自动Python环境设置和依赖管理
Kubernetes
io.mcp-cn.mcp-server-kubernetes
Kubernetes的MCP服务器,支持Kubernetes的读取和写入
AntV图表
io.mcp-cn.antv/mcp-server-chart
基于AntV的图表生成MCP工具,支持多种图表类型的创建和渲染
Excel MCP
io.mcp-cn.negokaz/excel-mcp-server
Excel文件的MCP服务器,支持Excel文件的读取和写入
Often paired with
insurance-advisor-china
v2.4.21
io.clawhub.mnetfairy/insurance-advisor-china
中国大陆AI保险顾问。为个人和家庭提供全方位的保险咨询、产品对比、方案设计、投保指导。当用户询问保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔等问题时使用。发布产物仅含 SKILL.md + 3 个只读参考文件(references/products.json、insurance-knowledge.md、compliance.md)+ 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗脚本与回归测试脚本是本地维护工具,不随发布产物分发。
ai-insurance-advisor
v2.4.21
io.clawhub.mnetfairy/ai-insurance-advisor
中国大陆保险顾问。本 skill 覆盖 8 项能力:保险需求分析(needs_analyzer.py)、产品对比(premium_calculator.py + 本地 products.json)、保费计算(premium_calculator.py)、方案设计(plan_designer.py)、保险知识问答(insurance-knowledge.md)、合规要点提示(compliance.md)、朋友圈/社交营销文案生成(agent LLM 生成,无专属脚本)、培训话术支持(agent LLM 生成,无专属脚本)。不提供核保预审、理赔代办、代理人展业工具等能力——这些场景请转人工或调用专业服务。发布产物仅含 SKILL.md + 3 个只读参考文件 + 3 个运行时脚本(needs_analyzer / premium_calculator / plan_designer);数据清洗与回归测试脚本为本地维护工具,不随发布产物分发。
中文公文写作
v2.0.63
io.clawhub.gongyu0918-debug/chinese-official-writing
用于中文公文、事务性材料和新闻稿件的起草、改写、压缩、润色、审校、文种核对、去口语化、降 AI 味及 Word 格式处理,适用于机关、企事业单位、学校和新闻机构。涵盖申请、请示、报告、通知、通告、意见、决定、决议、议案、公报、命令、函、复函、批复、说明、方案、纪要、公告、公示、通报、制度、规定、办法、细则、操作规程、工作要点、总结、调研、讲话、致辞、主持词、述职、可研、审查材料、技术需求、新闻消息、编者按、新闻评论,以及采购、整改、反馈和 AI 算力等场景。
Free Ride - Unlimited free AI
v1.1.0
io.clawhub.shaivpidadi/free-ride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Optional Groq, Gemini and Cerebras free tiers are opt-in. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
Keep exploring AgentHub
Most people compare similar tools or check scenario guides before installing—start here.
Listing badge: put AgentHub on your site
Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.
<a href="https://myagenthub.cn/p/io.github.yusasecurity/yusa" title="Listed on AgentHub: YUSA" target="_blank" rel="noopener">
<img src="https://myagenthub.cn/badge/io.github.yusasecurity/yusa?lang=en" alt="Listed on AgentHub: YUSA" height="20" style="border:0"/>
</a>[](https://myagenthub.cn/p/io.github.yusasecurity/yusa)Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.
Unified Manifest
{
"id": "io.github.yusasecurity/yusa",
"type": "mcp-server",
"version": "0.3.5",
"displayName": "YUSA",
"description": "Prompt-injection firewall for AI agents: scan untrusted text, fence it, gate tool calls.",
"repository": {
"url": "https://github.com/yusasecurity/yusa",
"source": "github"
},
"homepage": "https://yusasecurity.xyz",
"distribution": {
"packages": [
{
"registryType": "mcpb",
"identifier": "https://github.com/yusasecurity/yusa/releases/download/v0.3.5/yusa.mcpb",
"transport": "stdio",
"environmentVariables": [
{
"name": "YUSA_POLICY",
"description": "Optional path to a policy JSON (allowTools, allowAddresses, allowHosts, maxValueEth) for yusa_check_tool_call."
}
]
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"trae",
"cherry-studio",
"lingma",
"windsurf",
"cline",
"workbuddy"
],
"keywords": [],
"provenance": {
"origin": "official-mcp-registry",
"originalId": "io.github.yusasecurity/yusa",
"originalUrl": "https://registry.modelcontextprotocol.io/v0.1/servers/io.github.yusasecurity%2Fyusa/versions/latest",
"isOfficial": true,
"status": "active"
}
}