How to integrate MrScraper MCP with OpenAI Agents SDK

This guide walks you through connecting MrScraper to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working MrScraper agent that can create ai scrapers, collect web data, rerun your scrapers, and review scrape results through natural language commands. This guide will help you understand how to give your OpenAI Agents SDK agent real control over a MrScraper account through Composio's MrScraper MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

MrScraper logoMrScraper
Api Key

MrScraper is a web scraping API platform for structured extraction, search results, marketplace data, travel data, and web unblocking. Use it to turn messy web pages into clean, usable data without managing scraper infrastructure.

11 Tools

Introduction

This guide walks you through connecting MrScraper to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working MrScraper agent that can create ai scrapers, collect web data, rerun your scrapers, and review scrape results through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a MrScraper account through Composio's MrScraper MCP server.

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

Also integrate MrScraper with

TL;DR

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

What is OpenAI Agents SDK?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The MrScraper MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your MrScraper account. It provides structured and secure access to your scraper workflows, results, usage, and analytics, so your agent can create AI scrapers, rerun saved scrapers, retrieve results, repair manual workflows, and review scraping activity on your behalf.

  • AI scraper creation: Have your agent create and run general, listing, or map AI scrapers against websites.
  • Single and bulk scraper runs: Direct your agent to rerun saved AI or manual scrapers against one website or multiple websites at once.
  • Result tracking and retrieval: Let the agent list past scrape results, filter and sort them, then retrieve the current status and output of a selected run.
  • Manual scraper repair: Instruct your agent to repair a saved manual scraper when changes to its target website cause the workflow to stop matching.
  • Usage and performance monitoring: Have your agent review plan usage, token consumption, concurrency, rate limits, success rates, request volume, latency, and scraping trends over time.

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 OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live MrScraper project
  • Some knowledge of Python or Typescript
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
3

Install dependencies

npm install @composio/openai-agents @openai/agents dotenv

Install the Composio SDK and the OpenAI Agents SDK.

4

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

5

Import dependencies

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like MrScraper.
6

Set up the Composio instance

dotenv.config();

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});
What's happening:
  • dotenv.config() loads your .env file so COMPOSIO_API_KEY and USER_ID are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.
7

Create a Tool Router session

// Create Tool Router session for MrScraper
const session = await composio.create(userId as string, {
  toolkits: ['mrscraper'],
});
const mcpUrl = session.mcp.url;

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only mrscraper.
  • The router checks the user's MrScraper connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access MrScraper.
  • This approach keeps things lightweight and lets the agent request MrScraper tools only when needed during the conversation.
8

Configure the agent

// Configure agent with MCP tool
const agent = new Agent({
  name: 'Assistant',
  model: 'gpt-5',
  instructions:
    'You are a helpful assistant that can access MrScraper. Help users perform MrScraper operations through natural language.',
  tools: [
    hostedMcpTool({
      serverLabel: 'tool_router',
      serverUrl: mcpUrl,
      headers: { 'x-api-key': composioApiKey },
      requireApproval: 'never',
    }),
  ],
});
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access MrScraper and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a hostedMcpTool that connects to the MCP server URL we created earlier.
  • The headers object includes the Composio API key for secure authentication with the MCP server.
  • requireApproval: 'never' means the agent can execute MrScraper operations without asking for permission each time, making interactions smoother.
9

Start chat loop and handle conversation

// Keep conversation state across turns
const conversationSession = new OpenAIConversationsSession();

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

console.log('\nComposio Tool Router session created.');
console.log('\nChat started. Type your requests below.');
console.log("Commands: 'exit', 'quit', or 'q' to end\n");

try {
  const first = await run(agent, 'What can you help me with?', { session: conversationSession });
  console.log(`Assistant: ${first.finalOutput}\n`);
} catch (e) {
  console.error('Error:', e instanceof Error ? e.message : e, '\n');
}

rl.prompt();

rl.on('line', async (userInput) => {
  const text = userInput.trim();

  if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
    console.log('Goodbye!');
    rl.close();
    process.exit(0);
  }

  if (!text) {
    rl.prompt();
    return;
  }

  try {
    const result = await run(agent, text, { session: conversationSession });
    console.log(`\nAssistant: ${result.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();
});

rl.on('close', () => {
  console.log('\n👋 Session ended.');
  process.exit(0);
});
What's happening:
  • The program prints a session URL that you visit to authorize MrScraper.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using run().
  • The responses are printed to the console.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with MrScraper and OpenAI Agents SDK:

import 'dotenv/config';
import { Composio } from '@composio/core';
import { OpenAIAgentsProvider } from '@composio/openai-agents';
import { Agent, hostedMcpTool, run, OpenAIConversationsSession } from '@openai/agents';
import * as readline from 'readline';

const composioApiKey = process.env.COMPOSIO_API_KEY;
const userId = process.env.USER_ID;

if (!composioApiKey) {
  throw new Error('COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key');
}
if (!userId) {
  throw new Error('USER_ID is not set');
}

// Initialize Composio
const composio = new Composio({
  apiKey: composioApiKey,
  provider: new OpenAIAgentsProvider(),
});

async function main() {
  // Create Tool Router session
  const session = await composio.create(userId as string, {
    toolkits: ['mrscraper'],
  });
  const mcpUrl = session.mcp.url;

  // Configure agent with MCP tool
  const agent = new Agent({
    name: 'Assistant',
    model: 'gpt-5',
    instructions:
      'You are a helpful assistant that can access MrScraper. Help users perform MrScraper operations through natural language.',
    tools: [
      hostedMcpTool({
        serverLabel: 'tool_router',
        serverUrl: mcpUrl,
        headers: { 'x-api-key': composioApiKey },
        requireApproval: 'never',
      }),
    ],
  });

  // Keep conversation state across turns
  const conversationSession = new OpenAIConversationsSession();

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

  console.log('\nComposio Tool Router session created.');
  console.log('\nChat started. Type your requests below.');
  console.log("Commands: 'exit', 'quit', or 'q' to end\n");

  try {
    const first = await run(agent, 'What can you help me with?', { session: conversationSession });
    console.log(`Assistant: ${first.finalOutput}\n`);
  } catch (e) {
    console.error('Error:', e instanceof Error ? e.message : e, '\n');
  }

  rl.prompt();

  rl.on('line', async (userInput) => {
    const text = userInput.trim();

    if (['exit', 'quit', 'q'].includes(text.toLowerCase())) {
      console.log('Goodbye!');
      rl.close();
      process.exit(0);
    }

    if (!text) {
      rl.prompt();
      return;
    }

    try {
      const result = await run(agent, text, { session: conversationSession });
      console.log(`\nAssistant: ${result.finalOutput}\n`);
    } catch (e) {
      console.error('Error:', e instanceof Error ? e.message : e, '\n');
    }

    rl.prompt();
  });

  rl.on('close', () => {
    console.log('\nSession ended.');
    process.exit(0);
  });
}

main().catch((err) => {
  console.error('Fatal error:', err);
  process.exit(1);
});

Conclusion

This was a starter code for integrating MrScraper MCP with OpenAI Agents SDK to build a functional AI agent that can interact with MrScraper.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.
TOOLS

Supported Tools

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

Bulk Rerun AI Scraper

Run an existing General AI scraper configuration against multiple URLs in one request.

Bulk Rerun Manual Scraper

Run an existing saved manual scraper workflow against multiple URLs in one request.

Create AI Scraper

Create and run a general, listing, or map AI scraper against a website.

Get Account Usage

Return the connected MrScraper account's plan, token usage, concurrency allowance, and rate limits without exposing user identity or token details.

Get Scrape Status Analytics

Return aggregate scrape counts, success rate, request rate, latency, and status totals for a domain and action over a time range.

Get Scrape Analytics Timeline

Return time-series scrape activity and success metrics for a domain and action over a time range.

Get Scrape Result

Retrieve the current status and output for one accessible scrape result by ID.

Heal Manual Scraper

Ask MrScraper to repair an existing manual scraper workflow that no longer matches its target site.

List Scrape Results

List scrape results for the connected account with filtering, sorting, and agent-controlled pagination.

Rerun AI Scraper

Run an existing AI scraper configuration against a new URL, with optional map crawl controls.

Rerun Manual Scraper

Run an existing saved manual scraper workflow against a new URL.

FAQ

Frequently asked questions

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

Yes, you can. OpenAI Agents 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 MrScraper tools.

Yes, absolutely. You can configure which MrScraper 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 MrScraper data and credentials are handled as safely as possible.

Start with MrScraper.It takes 30 seconds.

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

Start building