创思大模型安全 MCP
About
A content security protection system for large language models, providing real-time risk identification and interception to ensure safe and compliant applications.
Details
- Author
- chuangsiaihub
- Categories
- Other, AI, Security
Jump to
Setup
Install 创思大模型安全 MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/chuangsiaihub/chuangsi-mcp-python
Follow the installation instructions in the repository README, then restart your MCP client.
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。
- 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
{ "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】" } } } }
- 登录 创思安全控制台
- 前往「APIKey 管理」创建 API Key
- 在「策略中心」获取策略标识
- 替换配置中的占位符 【】
- 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。
- 邮箱:service@chuangsiai.com
- 官网:https://chuangsiai.com
- 控制台:https://console.chuangsiai.com
A content security protection system for large language models, providing real-time risk identification and interception to ensure safe, compliant, and trustworthy model applications.
An MCP server for AI video generation. MCP server for AI video generation. Lets Claude, ChatGPT, OpenClaw , Hermes & other agents create AI videos and publish them to YouTube, TikTok, Instagram etc..
AI Bill of Materials generation — model cards, dataset provenance, supply chain transparency, CycloneDX format by MEOK AI Labs
MachineTranslation.com MCP provides AI-powered multilingual translation through the Model Context Protocol. It uses multi-model consensus to deliver high-confidence translations and can be connected to AI assistants such as Claude, ChatGPT, Cursor, and other MCP-compatible clients.
MCP server that gives AI agents (Claude, Cursor, Codex, etc.) access to the full Runware.ai API — image generation, video generation, audio generation, 3D, upscaling, background removal, captioning, and more.
Add one endpoint and Claude, Cursor, or any MCP client can make video, images, music, and speech in chat. 100+ models, one API key.
EU AI Act Article 50 watermarking compliance — C2PA metadata, AI-generated content labeling, provenance attestation for Nov 2026 deadline
AI traffic control plane (chaos governor): Redis prompt replay, compliant web ingest, SSO org ledger, Agent Shell. BYOK OpenAI-compatible ingress. Cursor optional; MCP is a compatibility client.
Growth marketing, SEO and GEO as agent tools: 41 tools for ranked growth moves, drafted deliverables, ship actions, and AI answer visibility across ChatGPT, Gemini, Perplexity and Google AI Overviews, hosted remote at https://afterlaunch.io/api/mcp with anonymous discovery and OAuth.
Compare LLM cost & latency on one prompt, translate PDF keeping layout, cited research, make PPTX
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
