Skip to main content
Glama
Baidu Cloud AI Content Safety MCP Server

Baidu Cloud AI Content Safety MCP Server

百度云大模型内容安全MCP Server

本代码仓库包含一个 MCP 服务器,它提供对百度云大模型内容安全功能的访问。

前提条件

在使用百度云大模型内容安全MCP Server之前,请确保你具备以下条件:

  1. Python 3.10 或更高版本

  2. 已安装uv用于运行MCP Server

Related MCP server: Baidu Vector Database MCP Server

使用方式

使用百度云大模型内容安全MCP Server的推荐方式是通过uv运行,而无需进行安装。

克隆代码仓库,执行以下命令:

git clone https://github.com/liangjunyu2010/mcp_server_safe_content_check.git
cd mcp_server_safe_content_check

随后,你可以直接通过uv运行,其中BAIDU_CLOUD_ACCESS_KEY_ID和BAIDU_CLOUD_SECRET_ACCESS_KEY根据实际需要修改:

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

或者,在src/mcp_server_safe_content_check/目录中修改.env文件来设置环境变量,再使用以下命令运行服务器:

uv run src/mcp_server_safe_content_check/server.py 

支持的应用程序

百度云大模型内容安全MCP Server可以与各种支持模型上下文协议的大语言模型应用程序配合使用:

  • Cursor:支持 MCP 的人工智能代码编辑器

  • 自定义 MCP 客户端:任何实现 MCP 客户端规范的应用程序

在 Cursor 中的使用方法

Cursor 也支持 MCP工具。你可以通过两种方式将百度MCP Server添加到Cursor中:

依次打开Cursor设置>功能>MCP,点击+添加新的MCP服务器按钮,在mcp.json中添加以下配置:

{
    "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": "****"
            }
        }
    }
}

重启 Cursor 或重新加载窗口。

可用工具

百度云大模型内容安全MCP Server提供以下工具:

输入检测操作

  • input_analyze: 检测输入内容

    • 参数:

      • text: 输入的文本内容

环境变量

百度云IAM创建 权限选择 AFDFullControlAccessPolicy

  • BAIDU_CLOUD_ACCESS_KEY_ID: 百度云授权ACCESS_KEY

  • BAIDU_CLOUD_SECRET_ACCESS_KEY: 百度云授权SECRET_KEY

使用样例

使用Cursor

Example : 检查文件内容是否存在不安全信息

帮忙检测下风险

Cursor将使用百度云大模型内容安全MCP Server提供的input_analyze来检测输入内容是否安全.

检测结果显示,该文本内容存在极高风险:
风险类型:犯罪相关内容(hitType: crime)
风险评分:0.998(满分1分)
处理建议:严禁传播(action: 2)
安全评估:内容不安全(isSafe: 0)

Available Tools

1 tool
input_analyzeC
Name:
    检测文本安全

Description:
    将文本进行检测,判断是否存在风险内容

Args:
    text:  待检测文本

Inputs: text (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 1 tool

    Disambiguation5/5

    With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a single, clear purpose: analyzing text for safety risks, which cannot be confused with any other tool in this set.

    Naming Consistency5/5

    The naming is trivially consistent as there is only one tool. The tool name 'input_analyze' follows a clear verb_noun pattern, and with no other tools to compare, it cannot exhibit any inconsistency.

    Tool Count2/5

    A single tool is too few for a server with the broad purpose of 'Baidu Cloud AI Content Safety,' which suggests capabilities like image analysis, video moderation, or multiple text checks (e.g., spam, hate speech). This minimal set severely limits the server's utility and scope.

    Completeness2/5

    The server is severely incomplete for content safety. It only handles text input analysis, missing obvious gaps like image or video safety checks, batch processing, or different risk categories (e.g., political, adult). This will cause agent failures when non-text content needs moderation.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A secure server that allows LLM applications like Claude to execute whitelisted system commands with user confirmation and comprehensive security features.
      -
    • A
      license
      B
      quality
      D
      maintenance
      A server that provides access to Baidu Cloud Vector Database functionality through the Model Context Protocol, enabling LLM applications to perform vector searches and database operations via natural language.
      14
      3
      Apache 2.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      A server that enables seamless integration with Yango Tech e-commerce platform through Claude Desktop and Cursor IDE, allowing users to query orders, products, inventory and other business data using natural language.
      11
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      A minimal Model Context Protocol server that provides a safety guardrail tool to check if provided context is free from code injection or harmful content.
      -