Stop Chatting.
Start Acting.

The ScrapingBee MCP Server connects your AI models to the live web, so they can browse, search, and extract data using our robust API that handles proxies, CAPTCHAs, and JavaScript rendering.

Get your free API key Explore Tools

based on 100+ reviews.

ScrapingBee MCP Server turning live web pages into structured JSON for AI agents

Model Context Protocol

The Power of a Universal Language for AI

The Model Context Protocol (MCP) is an open-source specification that allows AI models to reliably interact with external tools. It's a universal language between an AI (the client) and a tool provider like us (the server).

Instead of being limited to static training data, an MCP-enabled AI can request real-time actions and receive structured data back. This is the key to building powerful, autonomous agents.

Live Data Access

Access real-time information from any website.

Perform Actions

Go beyond text generation. Search, extract, and more.

JavaScript scenario actions such as click, search and scroll

Standardized & Reliable

A robust protocol ensures predictable results.

AI agent talking to ScrapingBee through the MCP protocol

The Toolbox

A Comprehensive Suite of Tools

Getting Started

Connect to Your AI in Minutes

Connect Cursor

1 Open Cursor Settings
2 Tools & Integrations
3 "New MCP Server" (this opens mcp.json) and add:

Cursor MCP Settings

// In Cursor MCP settings
{
  "mcpServers": {
    "scrapingbee": {
      "url": "https://mcp.scrapingbee.com/mcp",
      "headers": {
        "Authorization": "Bearer <your_api_key>"
      }
    }
  }
}

Connect Claude Desktop

1 Open Settings → Connectors → Add custom connector, and enter the URL below
2 In the Request headers section add an Authorization header with the value Bearer <your_api_key> (including the space)
3 Header authentication for connectors is in beta and still rolling out — if you don't see Request headers yet, use Claude Code instead. One command:

Claude Desktop Connector URL

https://mcp.scrapingbee.com/mcp

Claude Code

claude mcp add --transport http scrapingbee https://mcp.scrapingbee.com/mcp \
  --header "Authorization: Bearer <your_api_key>"

Connect ChatGPT

1 ChatGPT's in-app connector settings currently support only OAuth or no authentication, so the API key header cannot be set there
2 Connect through the OpenAI API instead, passing the key as an Authorization header:

OpenAI Responses API mcp tool

// OpenAI Responses API "mcp" tool
{
  "type": "mcp",
  "server_label": "scrapingbee",
  "server_url": "https://mcp.scrapingbee.com/mcp",
  "headers": {
    "Authorization": "Bearer <your_api_key>"
  }
}

Connect from Python

1 Install the official mcp Python SDK
2 Use its Streamable HTTP client to connect and list the available tools:

Python MCP Client

import asyncio
from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    url = "https://mcp.scrapingbee.com/mcp"
    auth = {"Authorization": "Bearer <your_api_key>"}
    async with streamablehttp_client(url, headers=auth) as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print(tools)

asyncio.run(main())

Frequently Asked Questions

How do I get a ScrapingBee API key?

An API key is required to use these tools. You can get a free key with 1,000 credits by registering here . Send the key as an


             Authorization: Bearer <your_api_key>

request header. Passing it as an


             ?api_key=

query parameter in the MCP URL still works but is deprecated and will be removed in Version 3.

When should I use premium_proxy or stealth_proxy?

Start without them. If you get blocked (e.g., receive an error or CAPTCHA page), try


             premium_proxy: true

. If you are still blocked,


             stealth_proxy: true

will help you to unblock it.

Can I scrape more than just text?

Yes. The server provides tools to get the full


             get_page_html

, take a


             get_screenshot

of the page (or a specific element), and even download files like images or PDFs using the


             get_file

tool.

How much does each request cost?

Each request will be charged based on the proxy and features you are using. For more details, you can refer to this link .

Stop Chatting. Start Acting.