mcp_server_safe_content_check

# Baidu Cloud Large Model Content Security MCP Server This code repository contains an MCP server that provides access to the [Baidu Cloud Large Model Content Security](https://cloud.baidu.com/doc/AIGC_SEC/s/qlxblhd5j) features. ## Prerequisites Before using the Baidu Cloud Large Model Content Security MCP Server, please ensure you meet the following requirements: 1. Python 3.10 or higher 2. [uv](https://github.com/astral-sh/uv) installed to run the MCP Server ## Usage The recommended way to use the Baidu Cloud Large Model Content Security MCP Server is to run it via `uv` without installation. Clone the code repository and execute the following commands: ``` git clone https://github.com/liangjunyu2010/mcp_server_safe_content_check.git cd mcp_server_safe_content_check ``` Then, you can run it directly using `uv`, modifying `BAIDU_CLOUD_ACCESS_KEY_ID` and `BAIDU_CLOUD_SECRET_ACCESS_KEY` as needed: ``` uv run src/mcp_server_safe_content_check/server.py uv run src/mcp_server_safe_content_check/server.py --BAIDU_CLOUD_ACCESS_KEY_ID ACCESS_KEY --BAIDU_CLOUD_SECRET_ACCESS_KEY SECRET_KEY ``` Alternatively, modify the `.env` file in the `src/mcp_server_safe_content_check/` directory to set environment variables, and then run the server using the following command: ``` uv run src/mcp_server_safe_content_check/server.py ``` ## Supported Applications The Baidu Cloud Large Model Content Security MCP Server can be used with various large language model applications that support the model context protocol: - **Cursor**: An AI code editor that supports MCP - **Custom MCP Client**: Any application that implements the MCP client specification ## How to Use in Cursor [Cursor also supports MCP](https://docs.cursor.com/context/model-context-protocol) tools. You can add the Baidu MCP Server to Cursor in two ways: Open `Cursor Settings` > `Features` > `MCP`, click the `+ Add New MCP Server` button, and add the following configuration in `mcp.json`: ```JSON { "mcpServers": { "safe-content-check": { "command": "uv", "args": [ "run", "--with", "mcp[cli]", "mcp", "run", "/PATH/mcp_server_safe_content_check/src/mcp_server_safe_content_check/server.py" ], "env": { "BAIDU_CLOUD_ACCESS_KEY_ID": "****", "BAIDU_CLOUD_SECRET_ACCESS_KEY": "****" } } } } ``` Restart Cursor or reload the window. ## Available Tools The Baidu Cloud Large Model Content Security MCP Server provides the following tools: ### Input Detection Operation - `input_analyze`: Analyze input content - Parameters: - `text`: The input text content ## Environment Variables [Create Baidu Cloud IAM](https://console.bce.baidu.com/iam/#/iam/accesslist) and select the permission `AFDFullControlAccessPolicy` - `BAIDU_CLOUD_ACCESS_KEY_ID`: Baidu Cloud authorized ACCESS_KEY - `BAIDU_CLOUD_SECRET_ACCESS_KEY`: Baidu Cloud authorized SECRET_KEY ## Usage Example ### Using Cursor #### Example: Check if the file content contains unsafe information ``` Please help check for risks ``` Cursor will use the `input_analyze` provided by the Baidu Cloud Large Model Content Security MCP Server to check if the input content is safe. ``` The detection result shows that the text content has a very high risk: Risk Type: Crime-related content (hitType: crime) Risk Score: 0.998 (out of 1) Recommended Action: Prohibit dissemination (action: 2) Safety Assessment: Content is unsafe (isSafe: 0) ```