testhub-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@testhub-mcpfetch https://example.com and convert it to markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
testhub-mcp
公共测试工具空间(Test Hub)—— 一个面向所有项目的远程测试工具 MCP。 基于 Model Context Protocol 的
streamable-http远程服务,可托管在 魔搭 ModelScope MCP 广场。
它解决什么
AI Agent 要跑测试,常常得自己装环境——费时、费流量、还常因硬件不够跑不起来。
testhub-mcp 把常用测试能力做成远程工具(Tool as a Service):Agent 只要连上这个 MCP,就能直接调用,零安装。
Related MCP server: webscout-mcp
工具(v0.1)
工具 | 作用 | 关键参数 |
| 对任意公网 URL 发 HTTP 请求(接口测试 / 连通性) |
|
| 抓取网页内容,默认转 markdown |
|
{
"ok": true,
"status": 200,
"headers": { "content-type": "application/json" },
"body": "{\"hello\":\"world\"}",
"elapsed_ms": 123.4,
"final_url": "https://api.example.com/v1/ping",
"truncated": false
}{
"ok": true,
"url": "https://example.com/",
"status": 200,
"content": "# Example Domain\n\nThis domain is for use in ...",
"start_index": 0,
"has_more": true,
"total_length": 12345,
"next_start_index": 5000
}内容过长时用
start_index分块读取(与魔搭官方fetch对齐)。
快速开始(本地)
pip install -r requirements.txt
python3 server.py # 默认监听 0.0.0.0:8000,端点 /mcp
# 或
MCP_TRANSPORT=sse PORT=8000 ./run.sh # 以 SSE 方式启动,端点为 /sse自测:
pip install -r requirements-dev.txt
pytest -q接入(客户端 / Agent)
把下面这段填进任意支持 MCP 的客户端(Cherry Studio / Claude Code / 自研 Agent 等):
{
"mcpServers": {
"testhub": {
"type": "streamable_http",
"url": "https://mcp.api-inference.modelscope.net/<YOUR-DEPLOY-ID>/mcp"
}
}
}详见 examples/:mcp.remote.json(远程)· mcp.local.json(本地)。
部署到魔搭(托管)
把本仓库推到 GitHub;
打开 https://modelscope.cn/mcp → 右上 「创建MCP」 → 「GitHub 快速创建」;
托管类型选 「可托管部署」,填入本仓库地址
https://github.com/tethila/testhub-mcp;服务配置 config 填(⚠️ 这就是平台的「启动命令」,必须带
command):{"mcpServers":{"testhub-mcp":{"command":"python","args":["-m","server"]}}}(拼起来即
python -m server;平台会拉取本仓库并用pyproject.toml安装依赖)提交后平台自动完成「拉代码 → uv 装依赖 → 部署到函数计算 → 生成 URL」,得到 长期 URL,填回客户端即可。
⚠️ 魔搭托管要求
streamable-http或sse,且服务需监听平台注入的PORT环境变量(本仓库已适配)。 若用uvx方式,可写:{"mcpServers":{"testhub-mcp":{"command":"uvx","args":["--from","git+https://github.com/tethila/testhub-mcp","testhub-mcp"]}}}
安全(重要)
作为公共工具,内置 SSRF 防护(见 security.py):
仅允许
http/https;域名解析出的任一 IP 落在内网/保留网段即拒绝;
覆盖 云元数据地址
169.254.169.254、回环、私有段、链路本地、组播等;单次响应体上限 512 KB,请求超时可控;
不保存任何数据、不硬编码凭证、无状态。
部署到公网前,请根据你的环境再复核一遍策略与限流。
目录结构
testhub-mcp/
├── server.py # MCP 服务入口(工具定义)
├── security.py # SSRF 防护
├── core.py # 纯函数:HTML→Markdown、截断
├── run.sh # 启动脚本(托管入口)
├── requirements.txt
├── requirements-dev.txt
├── examples/ # 客户端接入配置
└── tests/ # 单测(离线可跑)路线图
v0.1
http_request·fetch_pagev0.2
check_url(DNS/端口/证书/重定向)·assert_json·regex_extractv0.3 重测试(
run_pytest/ 浏览器冒烟)—— 需独立算力节点
许可
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Reliable web access for AI agents: smart HTTP, rotating proxies, and full-browser rendering.
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
Pay-per-use agent tools: schedule HTTP calls, extract pages, PDFs, OG images, QR codes, short links.
Web search and clean-text page fetch for AI agents, with SSRF protection.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables LLMs to make HTTP requests with OAuth2, session cookies, retry logic, and cURL command generation, while providing security features like SSRF protection and TLS enforcement.1MIT
- AlicenseAqualityAmaintenanceEnables AI agents to perform web searches, fetch and extract page content, and crawl sites with caching, rate limiting, and robots.txt compliance, all without needing API keys.11214 PyPI1MIT
- AlicenseAqualityBmaintenanceEnables AI agents to read RSS/Atom feeds, extract web page content as text or Markdown, search the web, and batch-fetch multiple URLs without building custom crawlers.5MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to perform API testing and security validation through a permission-gated, SSRF-protected, audited MCP tool layer.-