No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by NanGePlus · MCP Server · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is MCPTest safe to install? View the security audit →
1、项目介绍 1.1、主要内容 本期系列相关视频如下，按照发布的先后顺序: (第一期)[2024.12.10]Claude重大突破！发布MCP(模型上下文协议)，带你在LLM应用程序脚本中感受它，无需使用Claude Desktop桌面软件，支持类OpenAI风格大模型 主要内容:MCP介绍、MCP功能测试,LLM(支持OpenAI接口风格的大模型)应用程序调用MCP https://www.bilibili.com/video/BV1HBquYbE7t/ https://youtu.be/Jmo7rgbOXQ (第二期)[2024.12.12]Claude MCP应用Text2SQL用例，带你在LLM应用程序中感受它的丝滑，无需使用Claude Desktop桌面软件，支持类OpenAI风格大模型 主要内容:使用MCP实现LLM应用程序Text2SQL功能操纵MySQL数据库 https://www.bilibili.com/video/BV1ELq4YME8T/ https://youtu.be/yaLAqEMz45A (第三期)[2024.12.12]Claude MCP应用客户端同时访问和调用多个服务器资源和工具，无需使用Claude Desktop桌面软件，支持类OpenAI风格大模型 主要内容:MCP客户端同时访问多个MCP服务器，支持文件系统操作和Text2SQL功能操纵MySQL数据库 https://www.bilibili.com/video/BV1oNqaYJEUy/ https://youtu.be/tG-ZjOgrcSA (第四期)[2024.12.23]DuckDuckGo在线搜索、Fetch内容提取MCP服务器，访问和调用多个服务器资源和工具，支持阿里通义千问大模型、GPT大模型、Ollama本地开源大模型 主要内容:MCP客户端同时访问多个MCP服务器，支持文件系统操作、Text2SQL功能操纵MySQL数据库、在线搜索(DuckDuckGo搜索引擎)和网页内容提取 https://www.bilibili.com/video/BV1SckXY3E6S/
| Stars | 82 |
| Forks | 25 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 42.5415969366686/100 |
| Open Issues | 4 |
| Last Updated | 2025-04-14 |
| Created | 2024-12-09 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~404k |
Explore other popular mcp server tools:
MCPTest is MCP功能测试,编写LLM(支持OpenAI接口风格的大模型)应用程序调用MCP。MCP(模型上下文协议)是Claude开源的一种开放协议，可实现LLM应用程序与外部数据源和工具之间的无缝集成。. It is categorized as a MCP Server with 82 GitHub stars.
MCPTest is primarily written in Python.
You can find installation instructions and usage details in the MCPTest GitHub repository at github.com/NanGePlus/MCPTest. The project has 82 stars and 25 forks, indicating an active community.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: