Crawl4AISAFE
用于提供给本地开发者的 LLM的高效互联网搜索&内容获取的MCP Server, 节省你的token
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/weidwonder-crawl4ai-mcp-server)
[](https://smithery.ai/server/@weidwonder/crawl4ai-mcp-server)
这是一个基于MCP (Model Context Protocol)的智能信息获取服务器,为AI助手系统提供强大的搜索能力和面向LLM优化的网页内容理解功能。通过多引擎搜索和智能内容提取,帮助AI系统高效获取和理解互联网信息,将网页内容转换为最适合LLM处理的格式。
特性
- 🔍 强大的多引擎搜索能力,支持DuckDuckGo和Google
- 📚 面向LLM优化的网页内容提取,智能过滤非核心内容
- 🎯 专注信息价值,自动识别和保留关键内容
- 📝 多种输出格式,支持引用溯源
- 🚀 基于FastMCP的高性能异步设计
安装
方式1: 大部分的安装场景
- 确保您的系统满足以下要求:
- Python >= 3.9
- 建议使用专门的虚拟环境
- 克隆仓库:
git clone https://github.com/yourusername/crawl4ai-mcp-server.git cd crawl4ai-mcp-server
- 创建并激活虚拟环境:
python -m venv crawl4ai_env source crawl4ai_env/bin/activate # Linux/Mac # 或 .\crawl4ai_env\Scripts\activate # Windows
- 安装依赖:
pip install -r requirements.txt
- 安装playwright浏览器:
playwright install
方式2: 安装到Claude桌面客户端 via Smithery
通过 Smithery 将 Crawl4AI MCP 的 Claude 桌面端服务安装自动配置至您本地的 Claude 伸展中心:
npx -y @smithery/cli install @weidwonder/crawl4ai-mcp-server --client claude
使用方法
服务器提供以下工具:
search
强大的网络搜索工具,支持多个搜索引擎:
- DuckDuckGo搜索(默认): 无需API密钥,全面处理AbstractText、Results和RelatedTopics
- Google搜索: 需要配置API密钥,提供精准搜索结果
- 支持同时使用多个引擎获取更全面的结果
参数说明:
query: 搜索查询字符串num_results: 返回结果数量(默认10)engine: 搜索引擎选择- "duckduckgo": DuckDuckGo搜索(默认)
- "google": Google搜索(需要API密钥)
- "all": 同时使用所有可用的搜索引擎
示例:
# DuckDuckGo搜索(默认)
{
"query": "python programming",
"num_results": 5
}
# 使用所有可用引擎
{
"query": "python programming",
"num_results": 5,
"engine": "all"
}read_url
面向LLM优化的网页内容理解工具,提供智能内容提取和格式转换:
markdown_with_citations: 包含内联引用的Markdown(默认),保持信息溯源fit_markdown: 经过LLM优化的精简内容,去除冗余信息raw_markdown: 基础HTML→Markdown转换
fc2da3cba7bcOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add crawl4ai_mcp_server -- uvx crawl4ai_mcp_server
{
"mcpServers": {
"crawl4ai_mcp_server": {
"command": "uvx",
"args": [
"crawl4ai_mcp_server"
]
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
read_url | read | Crawl a webpage and return its content in a specified format. |
search | read | 执行网络搜索并返回结果。 |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
mcp, ddgs
Gates applied: no_behavioural_pass.
fc2da3cba7bcfull audit observations/trust-audit/mcp-server/weidwonder__crawl4ai.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | fc2da3cba7bc | SAFE | B | 89 | first audit |
Questions
What is the Crawl4AI MCP server?
用于提供给本地开发者的 LLM的高效互联网搜索&内容获取的MCP Server, 节省你的token
What tools does Crawl4AI expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Crawl4AI safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Crawl4AI need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (fc2da3cba7bc), read on 2026-10-07. The repository is watched and re-audited when it changes.