Safe Content Check
Provides access to Baidu Cloud's large model content security features.
About
The Safe Content Check server grants access to the content safety capabilities of Baidu Cloud's large language models, enabling users to analyze text inputs for potentially unsafe content. It is designed to integrate with applications supporting the Model Context Protocol (MCP), such as Cursor, and offers tools like input analysis to detect risks based on categories like crime, with associated risk scores and recommended actions.
Key Features
- Integrates with applications supporting the Model Context Protocol (MCP).
- 1 GitHub stars
- Supports configuration via environment variables for secure credential management.
- Provides detailed risk assessments including risk type, score, and recommended action.
- Analyzes text for potential risks using Baidu Cloud's content security model.
Use Cases
- Building custom MCP clients for content analysis.
- Automating content moderation workflows for large language model applications.
- Integrating content safety checks into AI code editors like Cursor.