SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Scrapegraph ai MCP with Claude Agent SDK

Connect Claude Agent SDK to Scrapegraph ai MCP. Extract product prices from amazon search results, summarize latest news headlines from bbc homepage, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Scrapegraph ai logoScrapegraph ai
Api Key

Scrapegraph ai is an AI-powered web scraping API that lets you extract structured data from any website using natural language prompts. Easily turn web pages into ready-to-use data for your apps and agents.

27 Tools

Introduction

This guide walks you through connecting Scrapegraph ai to the Claude Agent SDK using the Composio tool router. By the end, you'll have a working Scrapegraph ai agent that can extract structured data with AI, crawl websites, convert pages to Markdown, scrape search results, and check your credits through natural language commands.

This guide will help you understand how to give your Claude Agent SDK agent real control over a Scrapegraph ai account through Composio's Scrapegraph ai MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Scrapegraph ai with

Claude CodeClaude CoworkOpenAI Agents SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

Here's what you'll learn:
  • Get and set up your Claude/Anthropic and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Scrapegraph ai
  • Configure an AI agent that can use Scrapegraph ai as a tool
  • Run a live chat session where you can ask the agent to perform Scrapegraph ai operations

What is Claude Agent SDK?

The Claude Agent SDK is Anthropic's official framework for building AI agents powered by Claude. It provides a streamlined interface for creating agents with MCP tool support and conversation management.

Key features include:

  • Native MCP Support: Built-in support for Model Context Protocol servers
  • Permission Modes: Control tool execution permissions
  • Streaming Responses: Real-time response streaming for interactive applications
  • Context Manager: Clean async context management for sessions

What is the Scrapegraph ai MCP server, and what's possible with it?

The Scrapegraph ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scrapegraph ai account. It provides structured and secure access to powerful web scraping and data extraction tools, so your agent can perform actions like running AI-powered scrapers, converting webpages to markdown, monitoring job statuses, and managing your account usage with ease.

  • AI-powered web scraping and search: Instruct your agent to extract structured data from any website or perform detailed web searches with parsed, organized results.
  • Webpage to markdown conversion: Let your agent instantly convert any webpage into clean, readable markdown for easy documentation or analysis.
  • Automated job status tracking: Check on the progress and results of ongoing scraping, crawling, or conversion jobs to stay updated without manual effort.
  • Smart multi-page crawling: Direct the agent to launch intelligent crawlers that gather data across multiple linked pages in a single workflow.
  • Account usage monitoring and feedback: Retrieve your remaining credits, track API usage, and submit feedback on completed tasks—all through your AI agent.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Composio API Key and Claude/Anthropic API Key
  • Primary know-how of Claude Agents SDK
  • A Scrapegraph ai account
  • Some knowledge of Python
2

Getting API Keys for Claude/Anthropic and Composio

Claude/Anthropic API Key
  • Go to the Anthropic Console and create an API key. You'll need credits to use the models.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

npm install @anthropic-ai/claude-agent-sdk @composio/core dotenv

Install the Composio SDK and the Claude Agents SDK.

What's happening:

  • @composio/core provides Composio integration for Anthropic
  • @anthropic-ai/claude-agent-sdk is the core agent framework
  • dotenv/config loads environment variables
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
ANTHROPIC_API_KEY=your_anthropic_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID identifies the user for session management
  • ANTHROPIC_API_KEY authenticates with Anthropic/Claude
5

Import dependencies

import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

dotenv.config();
What's happening:
  • We're importing all necessary libraries including the Claude Agent SDK and Composio
  • The dotenv.config() function loads environment variables from your .env file
  • This setup prepares the foundation for connecting Claude with Scrapegraph ai functionality
6

Create a Composio instance and Tool Router session

async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

  const composio = new Composio({ apiKey: COMPOSIO_API_KEY });

  // Create Tool Router session for Scrapegraph ai
  const session = await composio.create(USER_ID, {
    toolkits: ['scrapegraph_ai'],
  });
  const mcpUrl = session?.mcp.url;
What's happening:
  • The function checks for the required COMPOSIO_API_KEY environment variable
  • We're creating a Composio instance using our API key
  • The create method creates a Tool Router session for Scrapegraph ai
  • The returned url is the MCP server URL that your agent will use
7

Configure Claude Agent with MCP

const options: Options = {
  permissionMode: 'bypassPermissions',
  mcpServers: {
    composio: {
      type: 'http',
      url: mcpUrl,
      headers: { 'x-api-key': COMPOSIO_API_KEY }
    }
  },
  systemPrompt: 'You are a helpful assistant with access to Scrapegraph ai tools via Composio.',
  maxTurns: 10,
};
What's happening:
  • We're configuring the Claude Agent options with the MCP server URL
  • permissionMode: 'bypassPermissions' allows the agent to execute operations without asking for permission each time
  • The system prompt instructs the agent that it has access to Scrapegraph ai
  • maxTurns: 10 limits the conversation length to prevent excessive API usage
8

Create client and start chat loop

const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
  });

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}
What's happening:
  • The readline interface is created to handle user input and output
  • The query function is used to send the user's input to the agent
  • The chat loop continues until the user types 'exit' or 'quit'
9

Run the application

try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}
What's happening:
  • The chat function is the entry point for the application
  • The try-catch block is used to handle any errors that occur

Complete Code

Here's the complete code to get you started with Scrapegraph ai and Claude Agent SDK:

import 'dotenv/config';
import readline from 'node:readline';
import { Composio } from '@composio/core';
import { query, type Options } from "@anthropic-ai/claude-agent-sdk";

async function chat() {
  const { COMPOSIO_API_KEY, USER_ID } = process.env;
  if (!COMPOSIO_API_KEY || !USER_ID) {
    throw new Error('COMPOSIO_API_KEY and USER_ID required in .env');
  }

  const composio = new Composio({ apiKey: COMPOSIO_API_KEY });
  const session = await composio.create(USER_ID, {
    toolkits: ['scrapegraph_ai']
  });
  const mcp_url = session?.mcp.url;

  const options: Options = {
    permissionMode: 'bypassPermissions',
    mcpServers: {
      composio: {
        type: 'http',
        url: mcp_url,
        headers: { 'x-api-key': COMPOSIO_API_KEY }
      }
    },
    systemPrompt: 'You are a helpful assistant with access to Scrapegraph ai tools via Composio.',
    maxTurns: 10,
  };

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: 'You: '
  });

  console.log('\nChat started. Type "exit" to quit.\n');

  let isProcessing = false;

  async function ask(prompt: string) {
    isProcessing = true;
    rl.pause();

    process.stdout.write('Claude is thinking...');
    const stream = query({ prompt, options });

    let firstChunk = true;
    for await (const msg of stream) {
      const content = (msg as any).message?.content || (msg as any).content;
      if (Array.isArray(content)) {
        for (const block of content) {
          if (block.type === 'text' && block.text) {
            if (firstChunk) {
              process.stdout.write('\r\x1b[K');
              process.stdout.write('Claude: ');
              firstChunk = false;
            }
            process.stdout.write(block.text);
          }
        }
      }
    }
    process.stdout.write('\n\n');

    isProcessing = false;
    rl.resume();
    rl.prompt();
  }

  rl.on('line', async (line) => {
    if (isProcessing) return;

    const input = line.trim();
    if (input === 'exit') {
      rl.close();
      process.exit(0);
    }
    if (input) await ask(input);
    else rl.prompt();
  });

  await ask('What can you help me with?');
}

try {
  await chat();
} catch (error) {
  console.error(error);
  process.exit(1);
}

Conclusion

You've successfully built a Claude Agent SDK agent that can interact with Scrapegraph ai through Composio's Tool Router.

Key features:

  • Native MCP support through Claude's agent framework
  • Streaming responses for real-time interaction
  • Permission bypass for smooth automated workflows
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

Every Scrapegraph ai action and event your agent gets out of the box.

Convert Webpage to Markdown (V2)

Tool to convert any webpage into clean, well-formatted Markdown with full parameter control.

Generate Schema

Generate or modify a JSON schema based on a search query for structured data extraction.

Get Agentic Scraper History

Retrieve paginated history of agentic scraper jobs.

Get Crawler History

Retrieve the history of crawler jobs for your account.

Get Credits

Retrieve credit information for your ScrapeGraphAI account, including remaining credits and usage.

Get Endpoint Suggestions

Tool to get AI-powered suggestions for creating scraping endpoints.

Get Live Session URL

Tool to get a URL for a live browser session.

Get Markdownify History

Tool to retrieve the history of markdownify webpage-to-Markdown conversion jobs.

Get Scrape History

Retrieve the history of scrape jobs from your ScrapeGraphAI account.

Get Searchscraper History

Get the history of searchscraper jobs with pagination support.

Get Sitemap History

Tool to retrieve the history of sitemap extraction jobs.

Get Smartscraper History

Tool to retrieve the history of smartscraper jobs.

Get Usage Timeline

Tool to retrieve usage timeline statistics for your ScrapeGraphAI account.

Get Webhook Logs

Retrieve webhook delivery logs for a crawler job.

List Scheduled Jobs

Retrieve a paginated list of all scheduled scraping jobs for your account.

Markdownify Status

Check the status and retrieve results of a Markdownify webpage-to-Markdown conversion job.

Save Endpoint Configuration

Tool to save custom scraping endpoint configurations to ScrapeGraphAI.

Search Scraper

Perform web searches and scrape results, with AI-powered structured extraction or raw Markdown content.

Check SearchScraper Status

Check the status and results of an asynchronous SearchScraper job.

SmartCrawler Status

Check the status and retrieve results of a SmartCrawler web crawling job.

Start Smart Scraper

Extract structured JSON from one URL, HTML document, or Markdown document using ScrapeGraphAI v2.

Look Up SmartScraper Request

Retrieve the v2 History record for a SmartScraper Extract request ID.

Start Smart Crawler (Async)

Start a multi-page SmartCrawler job for AI-powered structured data extraction or markdown conversion.

Submit Feedback

Submit feedback and ratings for completed ScrapeGraphAI requests.

Submit Product Feedback

Submit product feedback for ScrapeGraphAI.

Convert JSON to TOON Format

Convert a JSON object to TOON (Token-Oriented Object Notation) for compact LLM processing while maintaining data structure.

Validate API Key

Check whether your ScrapeGraphAI API key is valid and authorized for use before making other API calls.

FRAMEWORKS

How to build Scrapegraph ai MCP Agent with another framework

Claude Code logo

Claude Code

Use Scrapegraph ai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Scrapegraph ai MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Scrapegraph ai MCP with OpenAI Agents SDK

Codex logo

Codex

Use Scrapegraph ai MCP with Codex

OpenClaw logo

OpenClaw

Use Scrapegraph ai MCP with OpenClaw

Hermes logo

Hermes

Use Scrapegraph ai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Scrapegraph ai MCP with Atomic Agent

Google ADK logo

Google ADK

Use Scrapegraph ai MCP with Google ADK

LangChain logo

LangChain

Use Scrapegraph ai MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Scrapegraph ai MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Scrapegraph ai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Scrapegraph ai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Scrapegraph ai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Scrapegraph ai MCP with Pydantic AI

AutoGen logo

AutoGen

Use Scrapegraph ai MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Scrapegraph ai MCP server, the agents and LLMs can only access a fixed set of Scrapegraph ai tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Scrapegraph ai and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Claude Agent SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Scrapegraph ai tools.

Yes, absolutely. You can configure which Scrapegraph ai scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Scrapegraph ai data and credentials are handled as safely as possible.

Start with Scrapegraph ai.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Scrapegraph ai tool your agent needs.Free to start.

Start building