What kind of risk assessments does it provide?

It offers detailed risk assessments including risk type, a risk score, and a recommended action, helping you understand the severity and what to do next.

How do I configure the tool?

Configuration is done through environment variables, ensuring secure credential management for accessing Baidu Cloud services.

How does it integrate with applications?

It integrates with applications that support the Model Context Protocol (MCP), such as the Cursor IDE.

Can I use this to check code comments?

Yes, within a supported MCP IDE like Cursor, you can check code comments and other text for unsafe content.

Safe Content Check

Name: Safe Content Check
Author: liangjunyu2010

•

Provides access to Baidu Cloud's large model content security features.

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

01Integrates with applications supporting the Model Context Protocol (MCP).

021 GitHub stars

03Supports configuration via environment variables for secure credential management.

04Provides detailed risk assessments including risk type, score, and recommended action.

05Analyzes text for potential risks using Baidu Cloud's content security model.

Use Cases

01Building custom MCP clients for content analysis.

02Automating content moderation workflows for large language model applications.

03Integrating content safety checks into AI code editors like Cursor.