Skip to main content
Glama

Crawlee MCP

Ein lokaler Model Context Protocol-Server zum Abrufen von Webseiten, Crawlen und Erstellen von Screenshots mit Crawlee. Er läuft über stdio und funktioniert daher mit Claude Code, Claude Desktop, Codex, Cursor und jedem MCP-kompatiblen Client.

Werkzeuge

Werkzeug

Beschreibung

fetch_url

Ruft eine einzelne URL ab und gibt sauberes Markdown zurück

fetch_multiple

Ruft mehrere URLs parallel ab

crawl

Durchsucht eine Website, entdeckt Links und gibt Seiteninhalte zurück

screenshot

Erstellt einen PNG-Screenshot einer Seite

ping

Gesundheitscheck

Related MCP server: weblens-mcp

Installation

Erfordert Node.js 20 oder neuer. Die erste Verwendung von JavaScript-Rendering oder Screenshots erfordert außerdem den Chromium-Browser:

npx playwright install chromium

Sobald das Paket auf npm veröffentlicht ist, kann jeder Client es mit folgendem Befehl starten:

npx -y @patrikmichi/crawlee-mcp

Bis das npm-Paket veröffentlicht ist, installieren Sie es direkt von GitHub:

npx -y github:patrikmichi/crawlee-mcp

Client-Konfiguration

Claude Code

claude mcp add --transport stdio crawlee -- npx -y @patrikmichi/crawlee-mcp

Claude Desktop

Fügen Sie dies zu Ihrer Claude Desktop-Konfigurationsdatei hinzu:

{
  "mcpServers": {
    "crawlee": {
      "command": "npx",
      "args": ["-y", "@patrikmichi/crawlee-mcp"]
    }
  }
}

Codex

Fügen Sie dies zu ~/.codex/config.toml hinzu:

[mcp_servers.crawlee]
command = "npx"
args = ["-y", "@patrikmichi/crawlee-mcp"]

Andere MCP-Clients

Verwenden Sie denselben Befehl und dieselben Argumente: npx -y @patrikmichi/crawlee-mcp.

Konfiguration

cp env.example .env

Variable

Erforderlich

Beschreibung

CRAWLEE_PROXY_URLS

Nein

Kommagetrennte Proxy-URLs für Rotation

CRAWLEE_TIMEOUT_MS

Nein

Request-Timeout in ms (Standard: 30000)

CRAWLEE_STEALTH

Nein

Auf false setzen, um den Stealth-Modus zu deaktivieren (Standard: true)

Entwicklung

npm install
npm start          # Run with tsx (no build needed)
npm run build      # Compile TypeScript
npm run typecheck  # Type check only

Dieser Server ist bewusst lokal und nur über stdio nutzbar, da JavaScript-Rendering und Screenshots einen lokalen Playwright-Browser erfordern.

Available Tools

5 tools
crawlA

Crawl a website starting from a seed URL, following discovered links across multiple pages. Returns an array of {url, title, content} objects. Use link_pattern to restrict crawling to specific URL patterns (e.g. "https://example.com/blog/**").

Inputs: url (required), label, max_pages, render_js, +3 more.

fetch_multipleA

Fetch multiple URLs in parallel and return an array of {url, content, error} objects. Useful for bulk research or comparison tasks.

Inputs: urls (required), render_js.

fetch_urlB

Fetch a web page and return its content as clean markdown. Use render_js=true for JavaScript-heavy pages (SPAs, Twitter/X, etc). Use render_js=false for fast HTML-only fetching.

Inputs: url (required), render_js, extract_content.

pingB

Check that the crawlee MCP server is running.

Inputs: no named parameters.

screenshotB

Take a screenshot of a web page and return it as a base64-encoded PNG image.

Inputs: url (required), full_page.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: fetching a single page, fetching multiple pages in parallel, taking a screenshot, health checking, and crawling a website. There is no overlap or ambiguity between the tools.

    Naming Consistency5/5

    All tool names follow a consistent verb-based pattern using lowercase and underscores where needed (e.g., fetch_url, fetch_multiple). No mixing of styles like camelCase or inconsistent verb forms.

    Tool Count5/5

    With 5 tools, the server is well-scoped for web crawling and scraping. Each tool earns its place: single fetch, batch fetch, screenshot, full crawl, and a health check. The count is neither too thin nor excessive.

    Completeness4/5

    The tool set covers the core workflows of fetching pages and crawling sites, with parallel fetching and screenshot support. Minor gaps exist, such as advanced extraction capabilities or session management, but the surface is practical for typical use cases.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables web scraping and crawling capabilities for LLM clients, supporting single-page scraping, multi-page website crawling, and web search with multiple engines (Playwright, Cheerio, Puppeteer) and flexible output formats including markdown, HTML, text, and screenshots.
      7
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to fetch and render web pages (including JavaScript-heavy SPAs) with headless Chromium, extract readable content with Mozilla Readability, capture navigation links, download images, and return a clean markdown file path.
      1
      17 npm
      ISC