# How to integrate Scrape do MCP with LlamaIndex

```json
{
  "title": "How to integrate Scrape do MCP with LlamaIndex",
  "toolkit": "Scrape do",
  "toolkit_slug": "scrape_do",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/scrape_do/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/scrape_do/framework/llama-index.md",
  "updated_at": "2026-05-12T10:24:44.960Z"
}
```

## Introduction

This guide walks you through connecting Scrape do to LlamaIndex using the Composio tool router. By the end, you'll have a working Scrape do agent that can scrape product prices from a dynamic website, extract news headlines with javascript rendering, bypass cloudflare to get full page html through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Scrape do account through Composio's Scrape do MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Scrape do with

- [OpenAI Agents SDK](https://composio.dev/toolkits/scrape_do/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/scrape_do/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/scrape_do/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/scrape_do/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/scrape_do/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/scrape_do/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/scrape_do/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/scrape_do/framework/cli)
- [Google ADK](https://composio.dev/toolkits/scrape_do/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/scrape_do/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/scrape_do/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/scrape_do/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/scrape_do/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Scrape do
- Connect LlamaIndex to the Scrape do MCP server
- Build a Scrape do-powered agent using LlamaIndex
- Interact with Scrape do through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## What is the Scrape do MCP server, and what's possible with it?

The Scrape do MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scrape do account. It provides structured and secure access to robust web scraping tools, so your agent can perform actions like scraping dynamic pages, managing sessions, setting custom headers or proxies, and extracting structured data from any website on your behalf.
- Dynamic page scraping with headless browsers: Retrieve fully rendered HTML content from JavaScript-heavy or protected websites by leveraging advanced browser emulation and proxy rotation.
- Custom scraping session management: Set device type, cookies, wait times, and custom headers to imitate different users, maintain sessions, or access device-specific content for tailored data extraction.
- Proxy and anti-bot bypass control: Enable super or proxy modes to utilize residential, mobile, or datacenter proxies, helping your agent bypass strict anti-bot systems and geo-restrictions seamlessly.
- Targeted resource filtering: Block specific URLs like ads or analytics scripts during scraping to increase speed, avoid distractions, and improve privacy.
- Account usage and statistics retrieval: Access real-time usage stats, subscription status, and remaining request limits so your agent can monitor scraping quotas and avoid interruptions.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `SCRAPE_DO_CANCEL_ASYNC_JOB` | Cancel Async Job | Tool to cancel an asynchronous scraping job. Use when you need to stop processing of pending tasks in a job. Completed tasks remain available. |
| `SCRAPE_DO_CREATE_ASYNC_JOB` | Create Async Scraping Job | Tool to create an asynchronous scraping job with specified targets and options. Use when you need to scrape multiple URLs in parallel without waiting for results. Returns a job ID immediately for polling results later via the get job status action. |
| `SCRAPE_DO_GET_ACCOUNT_INFO` | Get Account Information | Retrieves account information and usage statistics from Scrape.do. This action makes a GET request to the Scrape.do info endpoint to fetch: - Subscription status - Concurrent request limits and usage - Monthly request limits and remaining requests - Real-time usage statistics Rate limit: Maximum 10 requests per minute. Use remaining request counts to monitor credits proactively, as different scraping operations (e.g., rendered-page requests) consume varying credit amounts and exhaustion mid-run causes failures. |
| `SCRAPE_DO_GET_AMAZON_OFFERS` | Get Amazon Product Offers | Get all seller offers for any Amazon product. Retrieves every seller listing including pricing, shipping costs, seller information, and Buy Box status in structured JSON format. Use when you need to compare prices across multiple sellers or find the best deal for a specific product. |
| `SCRAPE_DO_GET_AMAZON_PRODUCT` | Get Amazon product details | Extract structured product data from Amazon product detail pages (PDP). Returns comprehensive product information including title, pricing, ratings, images, best seller rankings, and technical specifications in JSON format. |
| `SCRAPE_DO_GET_AMAZON_RAW_HTML` | Get Amazon raw HTML | Tool to get raw HTML from any Amazon page with ZIP code geo-targeting. Use when you need complete unprocessed HTML source from Amazon URLs with location-based targeting. Ideal for scraping pages not covered by other structured endpoints. |
| `SCRAPE_DO_GET_ASYNC_ACCOUNT_INFO` | Get Async API Account Information | Tool to get account information for the Async API including concurrency limits and usage statistics. Use when you need to check available concurrency slots, active jobs, or remaining credits for Async API operations. |
| `SCRAPE_DO_GET_ASYNC_JOB` | Get Async Job Details | Tool to retrieve details and status of a specific asynchronous scraping job. Use when you need to check the progress, status, or results of a previously created async job. Returns job metadata including creation time, completion time, task counts, and detailed task list. |
| `SCRAPE_DO_GET_ASYNC_TASK` | Get Async Task Result | Tool to retrieve the result of a specific task within an asynchronous job. Returns the scraped content for that particular URL. Use when you need to check the status and result of a previously submitted async scraping task. |
| `SCRAPE_DO_SCRAPE_DO_GET_PAGE` | Scrape webpage using scrape.do | A tool to scrape web pages using scrape.do's API service. Makes a basic GET request to fetch webpage content while handling anti-bot protections and proxy rotation automatically. Does not execute JavaScript by default — pages requiring client-side rendering (SPAs, dynamically loaded content) will return incomplete HTML; use SCRAPE_DO_GET_RENDER_PAGE or set render=true for those cases. |
| `SCRAPE_DO_LIST_ASYNC_JOBS` | List Asynchronous Scraping Jobs | Tool to list all asynchronous scraping jobs. Returns paginated list of jobs with their status and metadata. Use when you need to retrieve job history or monitor job statuses. Supports pagination with up to 100 jobs per page. |
| `SCRAPE_DO_SCRAPE_DO_PROXY_MODE` | Use Scrape.do Proxy Mode | This tool implements the Proxy Mode functionality of scrape.do, which allows routing requests through their proxy server. It provides an alternative way to access web scraping capabilities by handling complex JavaScript-rendered pages, geolocation-based routing, device simulation, and built-in anti-bot and retry mechanisms. |
| `SCRAPE_DO_SCRAPE_URL_POST` | Scrape URL using POST method | Tool to scrape web pages using POST method via scrape.do API. Use when you need to send POST requests to target websites with custom request body data. Supports all parameters from GET endpoint plus request body customization for POST/PUT/PATCH methods. |
| `SCRAPE_DO_SEARCH_AMAZON` | Search Amazon products | Tool to search Amazon and scrape product listings with structured results. Performs keyword searches and returns structured product data including titles, prices, ratings, Prime status, sponsored flags, and position rankings in JSON format. Use when you need to search for products on Amazon marketplace or gather product information from search results. |
| `SCRAPE_DO_SET_BLOCK_URLS` | Block specific URLs during scraping | This tool allows users to block specific URLs during the scraping process. It's particularly useful for blocking unwanted resources like analytics scripts, advertisements, or any other URLs that might interfere with the scraping process or slow it down. It provides granular control by allowing users to specify URL patterns to block, thereby improving scraping performance and maintaining privacy. |
| `SCRAPE_DO_SET_REGIONAL_GEO_CODE` | Set Regional Geolocation for Scraping | This tool allows users to set a broader geographical targeting by specifying a region code instead of a specific country code. This is useful when you want to scrape content from an entire region rather than a specific country. Note that this feature requires super mode to be enabled and is only available for Business Plan or higher subscriptions. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Scrape do MCP server is an implementation of the Model Context Protocol that connects your AI agent to Scrape do. It provides structured and secure access so your agent can perform Scrape do operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Scrape do account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Scrape do

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Scrape do access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, scrape do)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Scrape do tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["scrape_do"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Scrape do actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Scrape do actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

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

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["scrape_do"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Scrape do actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Scrape do
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Scrape do, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["scrape_do"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Scrape do actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Scrape do actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

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

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["scrape_do"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Scrape do actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Scrape do to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Scrape do tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Scrape do MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/scrape_do/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/scrape_do/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/scrape_do/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/scrape_do/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/scrape_do/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/scrape_do/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/scrape_do/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/scrape_do/framework/cli)
- [Google ADK](https://composio.dev/toolkits/scrape_do/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/scrape_do/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/scrape_do/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/scrape_do/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/scrape_do/framework/crew-ai)

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Api sports](https://composio.dev/toolkits/api_sports) - Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Scrape do MCP?

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

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Scrape do tools.

### Can I manage the permissions and scopes for Scrape do while using Tool Router?

Yes, absolutely. You can configure which Scrape do 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.

### How safe is my data with Composio Tool Router?

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 Scrape do data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)