Decodo

Decodo MCP Server

Connect LLMs and AI agents to live web data using MCP (Model Context Protocol). The Decodo MCP Server lets you scrape websites, search engines, eCommerce platforms, and social media directly from AI tools like Claude, Cursor, and Windsurf, all without the need to build scraping infrastructure from scratch.

• Structured outputs in JSON, Markdown, and screenshots
• Server-side JavaScript rendering and anti-bot handling
• 125M+ IPs across 195+ locations

What is Decodo MCP server?

The Decodo MCP Server is a web scraping layer for AI agents. It connects MCP-compatible clients to Decodo's Web Scraping API, enabling:

• Web scraping for LLMs
• Real-time data retrieval for RAG
• AI agent browsing and research
• Structured data extraction from dynamic websites

Instead of maintaining proxies, parsers, and retry logic, you get a single integration point for reliable web data access.

Why use MCP for web scraping?

Model Context Protocol (MCP) is the emerging standard for connecting AI agents to external tools and data sources. With MCP:

• Agents can call tools dynamically
• Integrations stay standardized
• Workflows scale across environments

The Decodo MCP Server gives your agents reliable, production-ready web access through this standard.

Key features

Web scraping for AI agents, no infrastructure required. Scrape any website, including JavaScript-heavy pages, without handling proxy rotation, CAPTCHA solving, or anti-bot systems.

Structured outputs for LLM workflows. Markdown (LLM-ready), JSON (for structured pipelines), and screenshots (for visual context), built for RAG pipelines, AI research agents, and automation flows.

Built-in support for popular targets. Ready-made tools for Google and Bing (SERPs), Amazon, Walmart, and Target (eCommerce), TikTok and YouTube (social media), and ChatGPT and Perplexity (AI search).

Global proxy infrastructure. 125M+ residential IPs, 195+ geo-locations, and a 99.99% success rate on even the most protected targets.

Modular MCP toolsets. Enable only what you need: web, search, ecommerce, social_media, ai for cleaner tool selection and better agent performance.

Fast time to value. From API key to first scrape in minutes, no setup overhead.

Use cases

Use the Decodo MCP Server when you need web scraping for AI agents, structured data extraction at scale, reliable access to dynamic websites, real-time data for RAG, or an alternative to building scraping infrastructure from scratch. Common scenarios:

• AI-powered web scraping – give LLMs the ability to collect fresh data instead of relying on static training data.
• RAG with live data – pull real-time Google, Bing, and AI search results into retrieval pipelines.
• eCommerce intelligence – track product prices, listings, and sellers across marketplaces without getting blocked.
• Social media data collection – gather posts, channels, and engagement data from TikTok and YouTube.
• Travel and price aggregation – build tools that collect live pricing and availability across websites.

Quick start

1. Create a free account at dashboard.decodo.com – up to 10K free requests, no credit card required.
2. Get your API key. Copy your Web Data API key from your Web Data API subscription on the dashboard. Older plans have a basic authentication token, which also works (see Authentication).
3. Download Node.js 18+ from https://nodejs.org.
4. Get MCP client like Claude Desktop, Cursor, Windsurf or other MCP-compatible tools.
5. Configure the MCP server in your AI client (see configuration examples below).

Connecting to Decodo's MCP server

Open your preferred MCP client and add the following configuration (see examples for Claude Code, Cursor, Windsurf bellow):

{
  "mcpServers": {
    "Decodo": {
      "url": "https://mcp.decodo.com/mcp",
      "headers": {
        "Authorization": "Bearer <api_key>"
      }
    }
  }
}

Authentication

The local server reads either credential from SCRAPER_API_TOKEN and works out which one it got.

Claude Desktop

1. Open Claude Desktop → Settings → Developer → Edit Config.
2. Add to claude_desktop_config.json:

{
  "mcpServers": {
    "Decodo": {
      "command": "npx",
      "args": ["-y", "@decodo/mcp-server"],
      "env": {
        "SCRAPER_API_TOKEN": "<api_key>",
        "TOOLSETS": "web,ai"
      }
    }
  }
}

3. Save and restart Claude Desktop.

Cursor

1. Open Settings → MCP.
2. Click Add a new global MCP server (opens mcp.json).
3. Add the same configuration as above.
4. Save — look for a green status indicator next to Decodo.

Windsurf

1. Open Settings → Windsurf Settings.
2. Scroll to Cascade → Add custom server + (opens mcp_config.json).
3. Add the same configuration as above.
4. Save and restart Windsurf.

Test your setup

Once connected, try this prompt in your client:

▎ "Scrape the titles of the top 5 articles from Hacker News"

You should get a structured list back within seconds. If you see an auth error, double-check your API key on the dashboard.

Local development

Only needed if you want to change the server code.

Prerequisites

• Node.js 18.0+
• An MCP client - popular choices are Claude Desktop and Cursor

Step-by-step guide

1. Clone this repository:

git clone https://github.com/Decodo/mcp-server

2. Run the following commands in the terminal:

cd mcp-server
npm install
npm run build

3. Take note of your build location:

cd build/
pwd

Adding index.js to the end of this directory, your build file location should look something like this:

/Users/your.user/projects/mcp-server/build/index.js

4. Update your MCP client with the server information:

{
  "mcpServers": {
    "decodo-mcp": {
      "command": "node",
      "args": ["/Users/your.user/projects/mcp-server/build/index.js"],
      "env": {
        "SCRAPER_API_TOKEN": "<api_key>"
      }
    }
  }
}

Toolsets

Tools are organized into toolsets. Which ones you get depends on how you connect.

Claude (official connector)

The Decodo connector in Claude's connector directory includes the Web Data API tools only:

Any MCP client

You can selectively enable specific toolsets by passing a comma-separated list via the toolsets query parameter:

    "Decodo MCP Server": {
      "url": "https://mcp.decodo.com/mcp?toolsets=web,ai",
      "headers": {
        "Authorization": "Bearer <api_key>"
      }
    }

When no toolsets are specified, all tools are registered.

Tools

The server exposes the following tools:

Parameters

The following parameters are inferred from user prompts:

Examples

Scraping geo-restricted content

Query your AI agent with the following prompt:

Scrape peacock.com from a German IP address and tell me the pricing.

This prompt will say that peacock.com is geo-restricted. To bypass the geo-restriction:

Scrape peacock.com from a US IP address and tell me the pricing.

Limiting number of response tokens

If your agent has a small context window, the content returned from scraping will be automatically truncated, in order to avoid context-overflow. You can increase the number of tokens returned within your prompt:

Scrape hacker news, return 50k tokens.

If your agent has a big context window, tell it to return full content:

Scrape hacker news, return full content.

Use with Decodo agent skills

This server gives your agent the scraping tools. Decodo/agent-skills teaches it when to reach for them, which surface to use, and how to call it — so the agent picks the right tool and parameters on its own instead of guessing.

The skills route across the decodo CLI, this hosted MCP server, and the raw HTTP API, and fall back to the MCP server automatically when no shell is available. Pairing the two gives your agent both the execution layer (this server) and the decision layer (the skills) in a single setup.

Quick start (Claude Code):

/plugin marketplace add Decodo/agent-skills
/plugin install decodo@decodo-skills

See the agent-skills README for manual install and other agents (Cursor, Codex, Gemini CLI, Windsurf).

Related repositories

Web Scraping API, Decodo agent skills, Decodo OpenClaw skill

Try it

Plug Decodo MCP Server into your AI workflow in just a few clicks and equip your AI agents with real-time data from any website.

Start for free | Docs | Discord

License

All code is released under the MIT License.