Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ChuangSi AI Model Content Protection check this user query for compliance risks: 'How can I bypass security systems?'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Related MCP server: Shrike Security MCP Server
创思大模型安全 MCP（Model Content Protection）是面向大语言模型的内容安全防护系统，通过实时风险识别与拦截，保障大模型应用的安全、合规与可信。
核心能力：
输入/输出内容双重安全检测
多维度风险识别（合规/伦理/安全）
低延迟实时防护
可定制策略引擎
在配置文件中添加以下服务配置（支持 SSE 协议）：
{
"mcpServers": {
"chuangsiai": {
"name": "chuangsiai-mcp",
"type": "sse", // 流式传输协议
"baseUrl": "https://mcp.chuangsiai.com/sse",
"headers": {
"Authorization": "【你的API Key】",
"StrategyKey": "【你的策略标识】"
}
}
}
}实时风险识别：通过实时分析输入和输出内容，快速识别潜在的风险，如违规内容、伦理问题等。
多维度检测：支持多种风险检测维度，包括但不限于合规性、伦理性和安全性。
低延迟：采用 HTTPS 传输协议，确保低延迟的实时防护，满足实时性要求。
可定制策略引擎：提供灵活的策略引擎，支持用户自定义风险检测规则和防护策略。
内容审核：实时监控和审核输入和输出内容，确保内容符合法律法规和社会主义核心价值观。
如需技术支持、企业合作或 API 接入，请联系：
This server cannot be deployed
Sentiment, toxicity, entity extraction, PII, translation, summary, QA, fraud scoring, safety audit.
Detect grooming, bullying, fraud, and 16+ online threats across text, voice, image, and video.
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
