- Home
- MCP servers
- 百度云大模型内容安全MCP Server
百度云大模型内容安全MCP Server
- python
1
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"liangjunyu2010-mcp_server_safe_content_check": {
"command": "uv",
"args": [
"run",
"src/mcp_server_safe_content_check/server.py",
"--BAIDU_CLOUD_ACCESS_KEY_ID",
"ACCESS_KEY",
"--BAIDU_CLOUD_SECRET_ACCESS_KEY",
"SECRET_KEY"
],
"env": {
"BAIDU_CLOUD_ACCESS_KEY_ID": "ACCESS_KEY",
"BAIDU_CLOUD_SECRET_ACCESS_KEY": "SECRET_KEY"
}
}
}
}You can access Baidu Cloud large-model content safety capabilities through an MCP server that runs locally or remotely. This MCP Server exposes input analysis and related safety checks so your applications can screen content before processing it further, helping you enforce policies and reduce risk in user-generated content.
How to use
You can run the MCP Server with a lightweight runtime to analyze input text via a dedicated tool named input_analyze. Start the server using the runtime, then point your MCP client at the local or remote endpoint you configured. When you connect, your client can invoke the input_analyze operation to check whether a given text contains unsafe content. Use the provided environment variables to authorize access to Baidu Cloud services.
How to install
Prerequisites: Python 3.10 or higher and the uv runtime to start the MCP Server.
Clone the MCP Server repository and enter the project directory:
git clone https://github.com/liangjunyu2010/mcp_server_safe_content_check.git
cd mcp_server_safe_content_check
Run the MCP Server using uv directly without installation steps:
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, set environment variables in a local .env file within the server directory and then start the server with the standard run command:
uv run src/mcp_server_safe_content_check/server.py
Additional steps you may want to perform
If you prefer configuring environment variables through a file, place the following keys into a .env file inside src/mcp_server_safe_content_check/ and ensure the server picks them up when starting.
Available tools
input_analyze
Detects whether the provided input text contains unsafe content and returns a safety assessment for further processing.