
AI代理的网页浏览超能力——一台MCP服务器,用于抓取、爬取、提取、绘制、搜索、批处理、研究和监控网络。自托管,无API密钥。免费Firecrawl替代方案。
概览
抓取、提取、爬取、映射和搜索——自托管,无API密钥,无速率限制,无订阅。 PyreCrawl 支持(模型上下文协议),这是 Claude、Cursor、VS Code、Codex、OpenCode、Hermes 及任何兼容 MCP 代理的标准工具界面。 A总是选择最便宜且成功的方法: (无工具调用的只读状态):pyrecrawl://cache/stats ·pyrecrawl://sessions ·pyrecrawl://monitors (现成战术手册):研究(主题)·rag_ingest(网站)·watch_page(网址) 偏好选项:“自动”(默认梯级)·“快速”(仅HTTP)·“隐匿”(CF绕过)·“LLM”(深度处理)。 UV 是一个快速的 Python 包管理器,能处理 Python 本身——无需单独安装 Python。只下载一次: 然后直接运行 PyreCrawl——不使用 venv,不安装 pip 安装,不下载 Python:
概述(AI 翻译)
一个命令就能让任何AI代理掌握整个网络。 抓取、提取、爬行、绘制地图和搜索—— 自托管,没有API密钥,没有速率限制,没有订阅。
PyreCrawl 使用 MCP(模型上下文协议),这是 Claude 的标准工具接口, 光标、VS Code、Codex、OpenCode、Hermes 以及任何兼容 MCP 的代理。
智能自动备用梯总是选择最便宜且有效的方法:
⚡ 工具暴露
| 工具 | 它的作用 |
|---|---|
scrape(url, prefer="auto") |
单一URL→LLM兼容的标记下载 |
extract(url, schema) |
抓取 + 结构化提取(JsonCss 模式) |
map_site(root, include_pattern=None, limit=200) |
枚举所有内部网址 |
crawl(root, max_pages=5, prefer="auto", include_paths=None, exclude_paths=None, max_depth=0) |
多页爬行,带路径滤波器+真实BFS深度 |
document(url) |
PDF/DOCX/PPTX → 折扣(无浏览器,可选 [docs] 附加内容) |
search(query, limit=10) |
通过DuckDuckGo HTML进行网页搜索(无API密钥) |
search_papers(query, limit=8, source="arxiv", category=None) |
通过arXiv + Crossref进行学术检索(无API密钥)——将pdf_url输入到document |
| 'batch_scrape(urls[], … |
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
🔥 PyreCrawl — Web Browsing Superpowers for Your AI Agent
One command gives any AI agent the whole web. Scrape, extract, crawl, map, and search — self-hosted, no API keys, no rate limits, no subscription.
PyreCrawl speaks MCP (Model Context Protocol), the standard tool interface for Claude, Cursor, VS Code, Codex, OpenCode, Hermes, and any MCP-compatible agent.
A smart auto-fallback ladder always picks the cheapest method that succeeds:
fast HTTP
│ (403/503/Cloudflare challenge or empty body)
▼
stealth browser (real Chromium + Cloudflare solver)
│ (still blocked, or the page needs full JS rendering)
▼
deep processing (LLM-ready markdown, citations, structured extraction)
⚡ Tools exposed
| Tool | What it does |
|---|---|
scrape(url, prefer="auto") |
Single URL → LLM-ready markdown |
extract(url, schema) |
Scrape + structured extraction (JsonCss schema) |
map_site(root, include_pattern=None, limit=200) |
Enumerate all internal URLs |
crawl(root, max_pages=5, prefer="auto", include_paths=None, exclude_paths=None, max_depth=0) |
Multi-page crawl with path filters + true BFS depth |
document(url) |
PDF/DOCX/PPTX → markdown (no browser, optional [docs] extras) |
search(query, limit=10) |
Web search via DuckDuckGo HTML (no API key) |
search_papers(query, limit=8, source="arxiv", category=None) |
Academic search via arXiv + Crossref (no API key) — feed pdf_url into document |
batch_scrape(urls[], ...) |
Many URLs in ONE call — parallel, deduped, cache-aware |
deep_research(query, limit=5, scrape_top=3) |
Search → evidence pack with [n] citations (no LLM synthesis — your agent does that) |
monitor(url, action, css_selector=None) |
Change detection with persisted snapshots + unified diff |
session(session, action, ...) |
Persistent browser session (cookies kept) — login walls, multi-step flows, screenshots |
cache(action) |
Inspect/clear/enable/disable the HTTP response cache |
health() |
Versions + import sanity check |
安装
uvx --from pyrecrawl pyrecrawl serve配置
{
"mcpServers": {
"pyrecrawl": {
"command": "uvx",
"args": ["--from", "pyrecrawl", "pyrecrawl", "serve"]
}
}
}