Skip to main content
Glama
Sign In
gkzhb

Crawl4AI MCP Server

by gkzhb
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Crawl4AI Model Context Protocol Server

npm version GitHub stars GitHub issues GitHub license

This MCP Server helps you connect to your Crawl4AI docker API server.

Built with gkzhb/fastmcp-template: TypeScript MCP Server Template.

Quick Start

Prerequisites:

  • Node.js 18+

To start Crawl4AI MCP server:

export CRAWL4AI_URL=http://your-server-ip:port
npx -y @gkzhb/crawl4ai-mcp

Notice that the command above is for Crawl4AI server v0.6.x.

For Crawl4AI server before v0.6.0, please use 0.0.x:

npx -y @gkzhb/crawl4ai-mcp@0.0.8

This MCP server uses Streamable HTTP. And the default Streamable HTTP URL is http://localhost:8585/mcp. SSE is also supported and the SSE HTTP URL is http://localhost:8585/sse.

To customize MCP server, here are the shell environment variables:

Variable

If Optional

Description

CRAWL4AI_URL

Required

Crawl4AI docker API server URL, eg. http://localhost:11545

CRAWL4AI_API_TOKEN

Optional

If Crawl4AI server enables authentication, you need to use this

SERVER_PORT

Optional

MCP server port, default value is 8585

This MCP also supports Browserless to crawl web page since v0.2.1

See env.ts for Browserless environment variables:

  • BROWSERLESS_URL

  • BROWSERLESS_TOKEN

  • BROWSERLESS_BLOCK_ADS

  • BROWSERLESS_STEALTH_MODE

This server cannot be deployed

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Crawl4AI MCP Wrapper

    joedank
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables web scraping, crawling, and content extraction through Crawl4AI Docker API. Supports markdown extraction, screenshots, PDFs, JavaScript execution, and multi-URL crawling with reliable stdio transport.
    -

  • Firecrawl Local MCP

    ViperBlackSkull
    F
    license
    B
    quality
    D
    maintenance
    Provides web scraping, crawling, and site mapping capabilities by connecting directly to a self-hosted Firecrawl instance. It enables users to extract website content in markdown format and manage crawling jobs without an external API key.
    4
    1
    -

  • Coolify AnythingLLM MCP

    xlop-dev
    A
    license
    Not graded
    quality
    D
    maintenance
    Connects AnythingLLM to Coolify for natural language management of self-hosted infrastructure, including diagnostics, log fetching, and deployment automation.
    MIT

  • Augment-MCP-Proxy

    Windyhhh
    A
    license
    Not graded
    quality
    B
    maintenance
    Connects Augment to third-party Anthropic-compatible APIs locally, letting users keep full Augment functionality without spending Augment credits and while keeping code on their own machine.
    MIT