Skip to content
Claude Desktop

Claude Desktop Integration

Enable web scraping in Claude Desktop with CrawlForge MCP. Complete setup in under 5 minutes with a simple JSON configuration file.

Prerequisites

Claude Desktop
Download from claude.ai

Required

Node.js 18+
Install from nodejs.org

Required

API Key
Get from dashboard

Free

1
Install CrawlForge MCP Server
Install the CrawlForge MCP server package globally using npm.
Bash
npm install -g crawlforge-mcp-server

Dependencies, including crawlforge-extractors, install automatically.

2
Get Your API Key
Sign up for a free account and generate your API key.
  • Create a free account — Get 1,000 free credits—no credit card required. Sign Up Free
  • Navigate to API Keys — Go to Dashboard → API Keys
  • Generate a new key — Click "Create API Key" and copy the key (starts with cf_)
3
Configure Claude Desktop
Add CrawlForge MCP to Claude Desktop's configuration file.

macOS

Open the configuration file at:

Bash
~/Library/Application Support/Claude/claude_desktop_config.json

Add the following configuration:

Json
{
  "mcpServers": {
    "crawlforge": {
      "command": "npx",
      "args": ["-y", "crawlforge-mcp-server"]
    }
  }
}

Windows

Open the configuration file at:

Bash
%APPDATA%\Claude\claude_desktop_config.json

Add the following configuration:

Json
{
  "mcpServers": {
    "crawlforge": {
      "command": "npx.cmd",
      "args": ["-y", "crawlforge-mcp-server"]
    }
  }
}

Linux

Open the configuration file at:

Bash
~/.config/Claude/claude_desktop_config.json

Add the following configuration:

Json
{
  "mcpServers": {
    "crawlforge": {
      "command": "npx",
      "args": ["-y", "crawlforge-mcp-server"]
    }
  }
}
4
Restart and Test
Restart Claude Desktop and test the integration.
  • Restart Claude Desktop — Fully quit and relaunch the application
  • Open a new conversation — Start a fresh chat to load the MCP server
  • Test with a simple prompt — Try: "Use CrawlForge to fetch https://example.com"

Example Prompts

"Fetch the content from https://example.com"

"Extract all links from https://example.com"

"Get metadata from https://example.com"

Available Tools

After setup, Claude will have access to all 31 CrawlForge MCP tools:

ToolDescriptionCredits
fetch_urlFetch HTML from URLs1 credit
extract_textExtract clean text1 credit
extract_linksExtract all links1 credit
extract_metadataGet page metadata1 credit
scrape_structuredCSS selector extraction2 credits
batch_scrapeParallel batch scraping1/URL
deep_researchAI-powered research10 credits
search_webGoogle search integration5 credits

See the full API reference for all 31 tools and their parameters.

Troubleshooting

Tools Not Showing Up?

  1. Verify the config file path is correct for your OS
  2. Check JSON syntax is valid (use a JSON validator)
  3. Ensure Node.js 18+ is installed: node --version
  4. Restart Claude Desktop completely (not just close window)

Authentication Errors?

  1. Verify API key starts with cf_
  2. Check for spaces or quotes around the API key
  3. Generate a new API key from the dashboard
  4. Ensure key has not been deleted or expired

Rate Limit Issues?

  1. Check your plan's rate limits in the dashboard
  2. Free plan: 2 requests/second, 1,000 credits total
  3. Upgrade to a paid plan for higher limits
  4. Wait a few seconds between requests if hitting rate limits

Successfully integrated?

Explore all available tools and start building with AI-powered web scraping.