Skip to main content
Glama

🕷️ LookaCrawler

Kostenlose, quelloffene, token-effiziente lokale Alternative zu Firecrawl mit nativem Model Context Protocol (MCP)-Server für LLMs.

License: MIT Bun TypeScript MCP Ready GitHub Stars Local-First


📌 Warum LookaCrawler?

Web-Crawling für Large Language Models (LLMs) ist standardmäßig fehlerhaft: Moderne Webseiten enthalten massiven HTML-Ballast (Skripte, Tracking-Pixel, verschachtelte Divs, Navigations-Header, Stylesheets), was Tausende verschwendeter Tokens pro Seite kostet.

LookaCrawler ist ein quelloffener, token-optimierter lokaler Crawler, der >73 % bis 90 % des Web-Ballasts entfernt, sauberes Markdown extrahiert, mit Stealth-Playwright-Treibern Anti-Bot-Barrieren umgeht und einen nativen Model Context Protocol (MCP)-Server bereitstellt, der für Claude Desktop, Cursor und Antigravity bereit ist.


Related MCP server: TheCrawler

🥊 Vergleich: LookaCrawler vs. Alternativen

Funktion

🕷️ LookaCrawler

🔥 Firecrawl (Cloud)

⚡ Jina Reader

Preis / Kosten

$0.00 (100 % kostenlos & Open Source)

$16 bis $99+/Monat

Ratenlimitierte API

Token-Reduzierung

>73 % bis 90 % aggressives Entfernen

Standard-Markdown

Basis-Markdown

Datenschutz

100 % lokal (keine Telemetrie)

Cloud-Anbieter

Cloud-API

MCP-Integration

Nativer 1-Klick-Server (stdio & SSE)

Community-Wrapper

Keine

Stealth & Anti-Bot

Echtes Chrome + Stealth-Fingerprint

Cloud-Proxys

Basis-Header

Lokaler SQLite-Cache

Integriert (24h-TTL-Cache)

Redis / kostenpflichtiges Add-on

Keine

JS-SPA-Unterstützung

Playwright + Chrome-Pool

Cloud-Headless

Headless


🚀 Hauptfunktionen

  • Token-Ökonomie zuerst: Entfernt automatisch Skripte, Styles, Inline-SVGs, Tracking-Tags, Navigationen, Fußzeilen und redundante Formulare, bevor das Markdown an dein LLM übergeben wird.

  • Duale Hybrid-Crawling-Engine:

    • fast: Ultra-schneller nativer HTTP-GET mit Backoff. Eskaliert automatisch zu deep, wenn eine Anti-Bot-Herausforderung erkannt wird.

    • deep: Headless-Playwright-Engine, die echtes Google Chrome mit Stealth-Patches startet (navigator.webdriver entfernt, WebGL gespooft, CDP-Leaks bereinigt), um Cloudflare/Turnstile-geschützte Seiten transparent zu crawlen.

  • Natives MCP-Server-Protokoll: JSON-RPC-2.0-stdio- und SSE-Transporte, bereit für Claude Desktop, Cursor, Windsurf und Antigravity.

  • Lokales SQLite-Caching: Speichert extrahiertes Markdown in crawler_cache.sqlite, um doppelte Netzwerkaufrufe zu vermeiden.

  • Strukturierte JSON- & Metadaten-Extraktion: Extrahiert Open-Graph-Tags (og:title, og:description), Veröffentlichungsdaten, kanonische URLs und benutzerdefinierte CSS-Selektoren.


🔌 1-Klick-MCP-Setup (Claude Desktop & Cursor)

Füge LookaCrawler zu deiner claude_desktop_config.json oder den Cursor-MCP-Einstellungen hinzu:

{
  "mcpServers": {
    "lookacrawler": {
      "command": "bun",
      "args": ["run", "/absolute/path/to/lookacrawler/index.ts"]
    }
  }
}

Jetzt kannst du Claude oder Cursor auffordern:

„Crawle https://example.com/docs und extrahiere die API-Dokumentation mit LookaCrawler."


📦 Schnellstart & CLI-Nutzung

1. Installation

Erfordert Bun 1.1+ (oder Node.js 20+):

# Clone the repository
git clone https://github.com/lucasmartins-ai/lookacrawler.git
cd lookacrawler

# Install dependencies
bun install

2. CLI-Befehle

# Single URL fast Markdown extraction
bun run cli.ts extract https://news.ycombinator.com --mode fast

# Headless Playwright deep extraction with CSS selector target
bun run cli.ts extract https://example.com --mode deep --selector "main" --json

# Batch concurrent multi-URL crawling
bun run cli.ts batch https://site1.com https://site2.com --concurrency 4

# Structured JSON schema extraction
bun run cli.ts structured https://example.com --schema '{"title":"h1","links":"a"}'

# Start MCP Server via SSE on port 3000
bun run cli.ts serve --transport sse --port 3000

3. Docker-Deployment

# Build and run Docker container
docker build -t lookacrawler .
docker run -p 3000:3000 lookacrawler

🧪 Architektur & Tests

Incoming URL ──► [Local SQLite Cache Check] ──(Hit)──► Return Cached Markdown
                       │ (Miss)
                       ▼
            [Fast HTTP GET Request] ──(Blocked?)──► [Auto-Escalate to Deep Stealth]
                       │                                      │
                       ▼                                      ▼
            [HTML DOM Tree Parser] ◄──────────────────────────┘
                       │
                       ▼
       [Aggressive Token Noise Pruner]
       (Strips SVG, Nav, Ads, Tracking, CSS, JS)
                       │
                       ▼
         [Mozilla Readability Engine]
                       │
                       ▼
         [Turndown Markdown Converter] ──► Return Clean LLM Markdown

Test-Suite ausführen:

bun test

⭐ Mit Stern markieren & unterstützen

Wenn LookaCrawler dir API-Gebühren und Token-Kosten erspart:

  • ⭐ Markiere dieses Repository mit einem Stern, um anderen Entwicklern zu helfen, es zu finden!

  • 💡 Eröffne ein Issue / PR für neue Stealth-Bypasses oder Crawler-Funktionen.


Erstellt von LookADev

lookacrawler wird von LookADev entwickelt und gepflegt, einem Engineering-Studio, das sich auf KI-Agenten, Web-Architektur und Token-Optimierung spezialisiert hat.

Starte ein Projekt → lookadev.com · E-Mail: lucas@lookadev.com

📄 Lizenz

Open-Source-Software, lizenziert unter der MIT-Lizenz.

Available Tools

9 tools
batch_extract_web_contentA

Batch extract token-optimized Markdown from multiple website URLs concurrently, with aggregate token statistics.

What it does Runs the same fast/deep pipeline as extract_web_content across an array of up to 20 URLs in parallel, then returns per-URL results plus a summary (urls attempted, succeeded, failed, total tokens, and per-page token counts).

How to use

  • Use when you need many pages at once — docs, a list of product pages, a set of sources to compare.

  • mode applies to every URL. concurrency (1-10) caps parallel workers; keep it modest on fast machines / low bandwidth.

  • css_selector is applied to all URLs. headers/cookies/proxy apply globally to every request.

  • Each URL is independent: a single failure does not abort the batch (results carry an "error" field for that URL).

Returns Structured JSON with per-url markdown/tokens/error and aggregate totals. Incomplete or empty batches still return a valid result object.

Inputs: urls (required), mode, proxy, cookies, +4 more.

crawl_websiteB

Recursively crawl an entire website or documentation section with depth limits, URL pattern filtering, and token accounting.

Inputs: start_url (required), mode, max_depth, max_pages, +4 more.

deep_enrich_leadB

Deeply enrich a business lead by crawling its official website with LookaCrawler's token-optimized engine. Extracts verified emails, social media links (Instagram, LinkedIn), decision makers / founders, and generates a concise Markdown summary (<300 tokens) for LLMs.

Inputs: title (required), website (required), mode, phone, +4 more.

discover_local_leadsA

Discover local businesses, establishments, and B2B prospects using the Google Maps engine. Extracts title, category, formatted address, telephone, WhatsApp link, rating, review count, coordinates, and website URL.

Inputs: query (required), lang, limit, location.

extract_contactsA

Extract verified contact information (emails, phone numbers, WhatsApp links, and social media profiles) from a website and its contact subpages. Drastically saves tokens compared to feeding the entire raw DOM to the LLM.

Inputs: url (required), deep_scan.

extract_structured_dataA

Extract structured JSON — page metadata (Open Graph, canonical URL, author, dates) and/or a custom CSS-selector schema — from a website.

What it does Fetches a URL and returns a structured object. With include_metadata=true it reads Open Graph tags (og:title, og:description, og:image), the canonical URL, author, and publication/modified dates. You can also pass a schema (property name -> CSS selector) to pull specific fields (e.g. {"title": "h1", "price": ".price", "rating": "span.rating"}) into a typed object.

How to use

  • Use for product listings, news/metadata, schema-driven extraction, and any time you need fields instead of prose.

  • schema keys become the JSON keys; values are CSS selectors. Leave schema empty to get metadata only.

  • include_metadata (default true) adds the Open Graph / author / date block. Set false for a lean result.

  • mode/css_selector/headers/cookies/proxy behave exactly as in extract_web_content.

Returns JSON object with the requested fields (and/or metadata). Missing selectors are omitted rather than failing the whole call. Non-http or private URLs fail with isError: true.

Inputs: url (required), mode, proxy, schema, +5 more.

extract_web_contentA

Extract token-optimized, clean Markdown content from a target website for LLM consumption.

What it does Fetches a URL, strips HTML bloat (scripts, styles, inline SVGs, tracking tags, navigation, footers, redundant forms) and returns readable Markdown — cutting token usage by ~73% to 90% versus the raw page.

How to use

  • Use for any web page, article, or docs you want as LLM-ready text.

  • mode="fast" (default): native HTTP GET. mode="deep": headless Chrome with stealth fingerprint for JS-heavy or Cloudflare/Turnstile-protected pages.

  • css_selector scopes to a single element (e.g. "main", "article", "#content").

  • Pass headers/cookies for gated or geo-restricted content. Providing any of headers/cookies/proxy bypasses the SQLite cache.

  • No auth required. Respects robots/rate-limit via retry backoff.

Returns Markdown text. Cache hits are prefixed with a NOTE marker. Unsupported URLs (non-http, private IP, SSRF) fail with isError: true and a reason.

Inputs: url (required), mode, proxy, actions, +6 more.

map_websiteA

Discover the architecture and page inventory of a website domain via sitemaps, robots.txt, and link graphs. Returns a list of URLs with source and modification metadata. Useful for exploring a site before targeted crawling.

Inputs: url (required), max_links.

search_placesA

Search for local businesses, places, and establishments on Google Maps, extracting structured entity data (title, address, phone, website, coordinates, rating).

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 9 tools

    Disambiguation3/5

    Most tools target distinct actions, but two near-duplicate pairs stand out: discover_local_leads vs search_places (both pull the same Google Maps entity fields), and extract_contacts vs deep_enrich_lead (both crawl a business site for emails/socials). Descriptions add some differentiation, but an agent could easily misselect within these pairs.

    Naming Consistency5/5

    All names are snake_case and follow a verb_noun pattern (discover_local_leads, extract_contacts, crawl_website, map_website, search_places). Minor compounds like deep_enrich_lead and batch_extract_web_content are still readable and consistent with the convention.

    Tool Count5/5

    Nine tools is well within the sweet spot for a crawling/scraping server, and each tool covers a distinct capability tier (discovery, extraction, enrichment, batch, site mapping). No obvious padding or redundancy-driven bloat.

    Completeness4/5

    The surface covers the full lead-gen lifecycle: place discovery, contact extraction, lead enrichment, content/markdown extraction, recursive crawl, batch, structured extraction, and sitemap discovery. The main gap is a lack of a status/polling or pagination/continuation operation for long-running crawls or large result sets.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Open-source web scraper and extraction MCP server with JavaScript rendering, markdown output, PDF/DOCX parsing, structured errors, and validated extraction contract diagnostics for agents.
      2
      AGPL 3.0
    • A
      license
      A
      quality
      B
      maintenance
      A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.
      2
      14 npm
      20 PyPI
      4
      MIT

    Appeared in Searches