What can you do with this server?

The FineData MCP Server enables AI agents to scrape websites with advanced antibot bypass, JavaScript rendering, captcha solving, and proxy rotation. Core Features: * Scrape protected websites using antibot bypass for Cloudflare, DataDome, PerimeterX with TLS fingerprinting and Undetected Chrome mode * Render JavaScript pages with Playwright for SPAs (React, Vue, Angular) using configurable wait strategies (networkidle, load, domcontentloaded, CSS selectors) * Automatically solve captchas including reCAPTCHA, hCaptcha, Cloudflare Turnstile, and Yandex SmartCaptcha * Rotate through 87K+ proxies (datacenter, residential, mobile) with sticky sessions for authentication flows * Batch scrape up to 100 URLs simultaneously with parallel processing * Submit async scraping jobs for long-running requests (>60 seconds) with status tracking and webhook callbacks Management: * Monitor API usage and token consumption * Configure timeouts (5-300 seconds) and custom wait strategies * Track job status for async operations with smart retry logic and block detection * Integrate with AI tools like Claude Desktop, Cursor IDE, and GPT through MCP protocol

Which integrations are available for this server?

Enables bypassing Cloudflare antibot protections and solving Cloudflare Turnstile captchas to facilitate seamless web scraping of protected websites.

How do I use FineData MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@FineData MCP Server scrape https://example.com with javascript rendering and antibot bypass" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

FineData MCP Server

MCP (Model Context Protocol) server for FineData web scraping API.

Enables AI agents like Claude, Cursor, and GPT to scrape any website with:

Antibot Bypass - Cloudflare, DataDome, PerimeterX, and more
JavaScript Rendering - Full browser rendering with Playwright
Captcha Solving - reCAPTCHA, hCaptcha, Cloudflare Turnstile, Yandex
Proxy Rotation - 87K+ datacenter, residential, and mobile proxies
Smart Retry - Automatic retries with block detection
Markdown Output - Returns clean Markdown by default (optimized for AI agents)
AI Extraction - Extract structured data using natural language prompts (Qwen3-32B)

Installation

Using uvx (Recommended)

# Install uv if you haven't already curl -LsSf https://astral.sh/uv/install.sh | sh # Run directly with uvx FINEDATA_API_KEY=fd_xxx uvx finedata-mcp

Using pip

pip install finedata-mcp # Run FINEDATA_API_KEY=fd_xxx finedata-mcp

Using npx

npx -y @finedata/mcp-server

Configuration

Cursor IDE

Step 1: Open Cursor Settings → MCP

Or create/edit ~/.cursor/mcp.json:

macOS/Linux:

mkdir -p ~/.cursor && nano ~/.cursor/mcp.json

Windows:

%USERPROFILE%\.cursor\mcp.json

Step 2: Add FineData MCP server:

{ "mcpServers": { "finedata": { "command": "uvx", "args": ["finedata-mcp"], "env": { "FINEDATA_API_KEY": "fd_your_api_key_here" } } } }

Step 3: Restart Cursor

Step 4: Test by asking the agent:

"Scrape https://example.com and show me the title"

Alternative: Using npx (if uv not installed)

{ "mcpServers": { "finedata": { "command": "npx", "args": ["-y", "@finedata/mcp-server"], "env": { "FINEDATA_API_KEY": "fd_your_api_key_here" } } } }

Note: npx requires Python 3.10+ and uv/pipx installed. uvx is recommended.

Claude Desktop

Step 1: Open config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

Step 2: Add MCP server:

{ "mcpServers": { "finedata": { "command": "uvx", "args": ["finedata-mcp"], "env": { "FINEDATA_API_KEY": "fd_your_api_key_here" } } } }

Step 3: Restart Claude Desktop

Environment Variables

Variable	Required	Description
`FINEDATA_API_KEY`	Yes	Your FineData API key
`FINEDATA_API_URL`	No	API URL (default: https://api.finedata.ai)
`FINEDATA_TIMEOUT`	No	Default timeout in seconds (default: 60)

Available Tools

scrape_url

Scrape content from any web page with antibot bypass.

scrape_url( url: "https://example.com", formats: ["markdown"], # Output: markdown, rawHtml, text, links (default: ["markdown"]) only_main_content: true, # Extract main content only (default: true) extract_prompt: null, # AI extraction instruction (e.g. "Extract all product prices") use_js_render: false, # Enable Playwright for SPAs stealth_antibot: false, # Stealth mode for Cloudflare, DataDome (+7 tokens) stealth_antibot_headful: false, # Maximum bypass with real browser (+25 tokens) stealth_new: false, # Experimental engine (+15 tokens) use_residential: false, # Use residential proxy solve_captcha: false, # Auto-solve captchas timeout: 60 # Timeout in seconds )

Note: The MCP server returns Markdown by default (not raw HTML), which is optimized for AI agent consumption.

Token costs:

Base request: 1 token
Antibot bypass: +2 tokens
JS rendering: +5 tokens
Stealth Antibot: +7 tokens
Stealth Headful: +25 tokens
Stealth New: +15 tokens
Residential proxy: +3 tokens
Captcha solving: +10 tokens

scrape_async

Submit an async scraping job for long-running requests.

scrape_async( url: "https://heavy-site.com", use_js_render: true, timeout: 120, callback_url: "https://your-webhook.com/callback" )

Returns a job_id for status polling.

get_job_status

Get the status of an async scraping job.

get_job_status(job_id: "550e8400-e29b-41d4-a716-446655440000")

Statuses: pending, processing, completed, failed, cancelled

batch_scrape

Scrape multiple URLs in a single batch (up to 100 URLs).

batch_scrape( urls: ["https://example.com/1", "https://example.com/2"], use_js_render: false, callback_url: "https://your-webhook.com/batch-done" )

get_usage

Get current API token usage.

get_usage()

Examples

Basic Scraping

Ask Claude or your AI agent:

"Scrape https://example.com and show me the content"

JavaScript Rendered Page

"Scrape https://spa-website.com with JavaScript rendering enabled"

Protected Site with Captcha

"Scrape https://protected-site.com using residential proxy and captcha solving"

AI Data Extraction

"Scrape https://shop.com/products and extract all product names and prices"

Batch Scraping

"Scrape these URLs: https://example.com/1, https://example.com/2, https://example.com/3"

Pricing

FineData uses token-based pricing. Each feature adds tokens:

Feature	Tokens
Base request	1
Antibot (TLS fingerprinting)	+2
JS Rendering (Playwright)	+5
Stealth Antibot	+7
Stealth Headful	+25
Stealth New	+15
Residential Proxy	+3
Mobile Proxy	+4
reCAPTCHA / hCaptcha	+10
Cloudflare Turnstile	+12
Yandex SmartCaptcha	+15
AI Extraction (Qwen3-32B)	+5

Get your API key and free trial tokens at finedata.ai.

Troubleshooting

"No module named finedata_mcp"

Install uv and use uvx:

curl -LsSf https://astral.sh/uv/install.sh | sh

"externally-managed-environment" on macOS

This happens with Homebrew Python. Use uvx instead of pip:

{ "command": "uvx", "args": ["finedata-mcp"] }

MCP server not appearing in Cursor

Check ~/.cursor/mcp.json syntax (valid JSON)
Ensure FINEDATA_API_KEY is set
Restart Cursor completely
Check Cursor Output → MCP for errors

Support

Documentation: https://finedata.ai/docs
Email: support@finedata.ai
Issues: https://github.com/quality-network/finedata-mcp/issues

License

MIT

FineData MCP Server

FineData MCP Server

Installation

Using uvx (Recommended)

Using pip

Using npx

Configuration

Cursor IDE

Alternative: Using npx (if uv not installed)

Claude Desktop

Environment Variables

Available Tools

scrape_url

scrape_async

get_job_status

batch_scrape

get_usage

Examples

Basic Scraping

JavaScript Rendered Page

Protected Site with Captcha

AI Data Extraction

Batch Scraping

Pricing

Troubleshooting

"No module named finedata_mcp"

"externally-managed-environment" on macOS

MCP server not appearing in Cursor

Support

License

Resources

Tools

Latest Blog Posts

MCP directory API