«2Captcha»标志返回主页
如果网站速度慢,请使用网站链接 2captcha.cn

Web MCP server: Connect your AI to the internet

2Captcha Web MCP
  • Built-in captcha solving and WAF bypass
  • Web search & scraping
  • Extract data from any website
  • Browser automation

2Captcha Web MCP solves web access for LLMs and AI agents, allowing them to web search, protected page scraping, structured data extraction, browser automation, and captcha solving through a single MCP integration.

Your agent automatically uses the right tools for each task — from fast page access to a managed browser session with proxy and anti-bot support.

  • Anti-bot handling
  • Managed browser sessions
  • Works with any MCP client
  • Structured data extraction
  • Proxy support
  • 2,000,000+

    Developers worldwide have used the service

  • 1,200+

    Software products rely on the service

  • 500,000+

    Users earn through the affiliate program

The best customer experience provided by leading Web MCP

  • «G2»评级 - 4.5星(满分5星)
  • SourceForge»评级 - 4.5星(满分5星)
  • Captchathecat»评级 - 9.8星(满分10星)

How to get started

  • Create a 2Captcha account
  • Get your API key
  • Choose hosted or local MCP
  • Connect the MCP server to your AI client
  • Send your task to the AI agent

How 2Captcha Web MCP works

Give your AI agent a task. 2Captcha MCP selects the appropriate tools, handles web access, and returns the result.

  1. Give your agent a task

    Ask your AI to search, scrape, extract data, interact with a website, or solve a captcha.

  2. Select the right tools

    The agent uses the available MCP tools based on what the task requires.

  3. Access the website

    2Captcha MCP fetches the page directly or uses proxies and a managed browser when required.

  4. Handle protection

    Anti-bot checks, JavaScript rendering, browser sessions, and captcha challenges are handled as needed.

  5. Get the result

    Your agent receives page content, structured data, browser output, or a captcha solution and continues the workflow.

Connect 2Captcha Web MCP server

Connect 2Captcha MCP to your AI client using the hosted server or run the official package locally.

Hosted MCP: Connect directly without installing or running your own server.

Local MCP: Run the official @2captcha/mcp package locally with npx.

MCP clients: Works with Claude Code, Claude Desktop, Cursor, VS Code, and other MCP-compatible clients.

Connect directly to the hosted MCP server using your API key.

URL: https://mcp.2captcha.com/mcp
Authorization: Bearer YOUR_API_TOKEN

Connect Claude Code directly to the hosted MCP server.

claude mcp add --transport http 2captcha https://mcp.2captcha.com/mcp \
  --header "Authorization: Bearer YOUR_API_TOKEN"

Run the official @2captcha/mcp package locally with npx.

{
  "mcpServers": {
    "2captcha": {
      "command": "npx",
      "args": ["@2captcha/mcp"],
      "env": {
        "API_TOKEN": "YOUR_API_TOKEN"
      }
    }
  }
}

Run the official @2captcha/mcp package locally with npx.

{
  "mcpServers": {
    "2captcha": {
      "command": "npx",
      "args": ["@2captcha/mcp"],
      "env": {
        "API_TOKEN": "YOUR_API_TOKEN"
      }
    }
  }
}

Run the official @2captcha/mcp package locally with npx.

{
  "servers": {
    "2captcha": {
      "command": "npx",
      "args": ["@2captcha/mcp"],
      "env": {
        "API_TOKEN": "YOUR_API_TOKEN"
      }
    }
  }
}

Use cases

Data extraction & e-commerce

Data extraction & e-commerce

Collect structured data from product pages, listings, and other websites, including pages that require additional access handling.

Product & marketplace data

Extract titles, prices, ratings, sellers, stock, offers, and other product information into structured JSON.

Large-scale data collection

Process multiple pages and URLs without building a separate scraping workflow for every source.

AI & LLM workflows

AI & LLM workflows

Give AI agents access to current web data for research, RAG, analysis, and automated workflows.

RAG & agent tooling

Let AI agents search the web, access pages, and receive clean Markdown or structured JSON for further processing.

Dataset gathering

Collect fresh text and structured data from multiple web sources for datasets, analysis, and model workflows.

Web research & monitoring

Web research & monitoring

Search websites, collect relevant information, and track changes across multiple sources.

Web research

Find relevant pages, scrape their content, and extract the information needed for analysis or comparison.

Monitoring

Track prices, availability, listings, content changes, and other data that needs to be checked regularly.

Browser automation

Browser automation

Use a managed browser when a task requires interaction, JavaScript rendering, authentication, or persistent session state.

Interactive workflows

Navigate pages, click, type, scroll, fill forms, run JavaScript, and capture screenshots or page content.

Authenticated sessions

Save and restore login states so agents can continue multi-step workflows without starting a new session each time.

Automate websites in a managed browser

When a task requires real browser interaction, your AI agent can navigate pages, click, type, scroll, run JavaScript, capture screenshots, and work with dynamic content through 2Captcha MCP.

Interact with pages

Navigate, click, type, select options, scroll, hover, and perform multi-step actions.

Read and capture content

Get page text or HTML, run JavaScript, take screenshots, and save pages as PDF files.

Turn web pages into structured data

2Captcha MCP can extract useful data from web pages and return it in a format your AI agent can work with directly.

Extract exactly what you need:

Define the fields you want and receive structured JSON that matches your schema.

Process multiple pages:

Run scraping and parsing tasks across many URLs without handling each page individually.

Connect your AI to the web with 2Captcha MCP

Search, scrape, extract structured data, automate browser workflows, and handle protected websites through one Web MCP connection.

FAQ

What is 2Captcha MCP?
2Captcha MCP is a Model Context Protocol server that gives AI agents tools for web search, scraping, structured data extraction, browser automation, and captcha solving.
Which AI clients can I use?
It works with Claude Code, Claude Desktop, Cursor, VS Code, and other MCP-compatible clients.
Do I need to install anything?
No. You can connect directly to the hosted MCP server. A local version is also available through the official @2captcha/mcp package.
Can it access protected websites?
Yes. Web access can automatically use additional anti-bot handling, proxies, a managed browser, and captcha solving when required.
Can it automate browser actions?
Yes. AI agents can navigate pages, interact with elements, run JavaScript, capture content, and work with saved browser sessions.
Can it return structured data?
Yes. Pages or text can be converted into structured JSON using a defined schema, and marketplace pages can be parsed into product and listing data.
Can it solve captchas directly through MCP?
Yes. Captcha solving is available as part of the MCP toolset for supported captcha types.
  • «GDPR»标志
  • «SSL secured»标志
  • «Google privacy policy»标志
  • «S/MIME»标志
  • «CCPA»标志