Skip to main content

​
What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to connect directly to external tools and data sources. Crawleo provides native MCP support, allowing AI assistants to search the web and crawl URLs without custom integration code.

​
MCP Endpoint

https://api.crawleo.dev/mcp

​
Available Tools

When connected via MCP, AI assistants have access to five tools:

search_web

Bing-powered web search with auto-crawling. Best for LLM and RAG use cases.Cost: 10 credits per page of results

google_search

Google SERP data with knowledge graphs, news, images, places, and shopping.Cost: 10 credits per request

google_maps

Search for businesses, places, and landmarks on Google Maps.Cost: 10 credits per request

crawl_web

Crawl specific URLs and extract content.Cost: 1-10 credits per page

headful_browser

Premium headed browser crawling with advanced anti-bot evasion. For sites that block standard crawlers.Cost: 50 credits per URL

​
Credit Costs for MCP Tools

ToolCredits Cost
search_web10 credits per page
google_search10 credits per request
google_maps10 credits per request
crawl_web (HTTP request)1 credit per URL
crawl_web (browser rendering)10 credits per URL
headful_browser50 credits per URL
The AI will automatically choose the right tool for your request. headful_browser is only invoked when a site blocks standard crawling — the AI tries crawl_web first to save credits.

Credits & Pricing

View full pricing details and subscription plans.

​
Compatible Platforms

Crawleo MCP works with all major AI assistants and development environments:

Claude Desktop

Anthropic’s Claude desktop application.

Cursor IDE

AI-powered code editor.

Windsurf IDE

Codeium’s AI development environment.

GitHub Copilot

GitHub’s AI pair programmer.

​
Why Use MCP?

Connect AI assistants to Crawleo without writing any integration code. Just configure and go.
AI assistants can naturally decide when to search the web or crawl pages based on your requests.
Give your AI assistant access to live web data, not just its training data.
Same strict privacy guarantees as the REST API - no data retention, no training on your data.

​
Quick Setup

The basic configuration pattern is the same across all platforms: 
{
  "mcpServers": {
    "crawleo": {
      "url": "https://api.crawleo.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Select your platform from the navigation to see detailed setup instructions.

​
Example Usage

Once configured, you can ask your AI assistant things like:
  • “Search for the latest news about artificial intelligence”
  • “Crawl this documentation page and summarize it”
  • “Find and compare pricing from these three websites”
  • “Research the top Python web frameworks and their features”
The AI will automatically use Crawleo’s tools to fetch real-time web data.

​
Video Tutorials

Step-by-step video guides for setting up Crawleo MCP across different platforms:

​
IDE Integrations

​
AI Assistants

​
Tools & Automation

​
Resources

MCP.so Listing

View Crawleo on MCP.so directory.

GitHub Examples

Code examples and integrations.
Last modified on April 16, 2026