MCP.Market

PyreCrawl MCP server

by SanggonBoy·io.github.SanggonBoy/PyreCrawl·v0.8.1·18 stars
No reviews yet

Web scraping + research toolkit for AI agents: scrape, crawl, monitor URLs with anti-bot bypass.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

18 stars46 downloads/wk

Reviews

Write one

Nobody has reviewed PyreCrawl yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

PyreCrawl tools (13)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • batch_scrape

    Scrape MANY URLs in ONE call (parallel, deduped, cache-aware).

  • cache

    Inspect the response cache: stats, clear, enable, or disable.

  • crawl

    Multi-page crawl: discover URLs on `root`, then scrape each.

  • deep_research

    Search the web, then pull the top sources as EVIDENCE (no LLM synthesis).

  • document

    Extract text from a PDF/DOCX/PPTX URL → markdown (no browser).

  • extract

    Scrape + structured extraction using a CSS-based JSON schema.

  • health

    Verify PyreCrawl is working: engine versions, dependencies, update status.

  • map_site

    Enumerate all internal URLs reachable from `root`.

  • monitor

    Track a URL over time and report meaningful content changes.

  • scrape

    Scrape a single URL → LLM-ready markdown.

  • search

    Web search via DuckDuckGo HTML (no API key required).

  • search_papers

    Search academic papers via arXiv or Crossref — no API keys.

  • session

    Drive a persistent browser session — cookies & JS state kept across calls.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan10 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 11 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How PyreCrawl compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 85% of 866 Scraping and browsing servers
Tools
13
the typical Scraping and browsing server has 6
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
18
more than 85% of 583 Scraping and browsing servers
Downloads a week
46
more than 30% of 309 Scraping and browsing servers with a package

What its tools let an agent do: 13 read

Release history: 3 versions in the registry since 2026-09-11, latest 2026-09-21, typically one every 8 days.

Install PyreCrawl in Claude Code, Cursor or VS Code

claude mcp add PyreCrawl -- uvx pyrecrawl
Add to Cursor

What the publisher says

From the PyreCrawl repository's README, as published. We do not edit it. Read it on GitHub

🔥 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

MCP Resources (read-only state without a tool call): pyrecrawl://cache/stats · pyrecrawl://sessions · pyrecrawl://monitors

MCP Prompts (ready-made playbooks): research(topic) · ragingest(site) · watchpage(url)

Env flags

prefer options: "auto" (default ladder) · "fast" (HTTP only) · "stealth" (CF bypass) · "llm" (deep processing).

🚀 Install & Use (one-liner)

1. Install

UV (recommended — one command, zero Python setup)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

PyreCrawl: common questions

Is PyreCrawl MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the PyreCrawl safety report
How do I install PyreCrawl?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does PyreCrawl need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is PyreCrawl maintained?
The last commit was 44 days ago (2026-09-21). The latest release is v0.8.1.
What can I use instead of PyreCrawl?
Servers from other publishers that do the same job: fastCRW MCP server, CRW Web Scraper MCP server and Svipall MCP server. Compare all PyreCrawl alternatives.
How does PyreCrawl compare with other Scraping and browsing MCP servers?
safety score 92/100 (higher than 85% of 866 Scraping and browsing servers); tools 13 (the typical Scraping and browsing server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to PyreCrawl

Same job from other publishers: the closest match first, then the best rated.

All PyreCrawl alternatives →
  • fastCRW
    Scrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents.
    More from us →
    A
  • CRW Web Scraper
    Open-source web scraper for AI agents with scrape, crawl, and map tools
    A
  • Svipall
    Read any page past its anti-bot wall, crawl sites, search without an API key, solve captchas locally
    C
  • WebReaper
    AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.
    A
  • Anakin
    Web data for AI agents: scrape, crawl, search, deep research, site monitoring, browser automation
    B