# How to integrate Hyperbrowser MCP with LlamaIndex

```json
{
  "title": "How to integrate Hyperbrowser MCP with LlamaIndex",
  "toolkit": "Hyperbrowser",
  "toolkit_slug": "hyperbrowser",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/hyperbrowser/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/hyperbrowser/framework/llama-index.md",
  "updated_at": "2026-05-06T08:16:05.497Z"
}
```

## Introduction

This guide walks you through connecting Hyperbrowser to LlamaIndex using the Composio tool router. By the end, you'll have a working Hyperbrowser agent that can start a browser session with stealth mode, extract all product titles from this url, check status of your ongoing scrape job through natural language commands.
This guide will help you understand how to give your LlamaIndex agent real control over a Hyperbrowser account through Composio's Hyperbrowser MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Hyperbrowser with

- [OpenAI Agents SDK](https://composio.dev/toolkits/hyperbrowser/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/hyperbrowser/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/hyperbrowser/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/hyperbrowser/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/hyperbrowser/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/hyperbrowser/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/hyperbrowser/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/hyperbrowser/framework/cli)
- [Google ADK](https://composio.dev/toolkits/hyperbrowser/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/hyperbrowser/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/hyperbrowser/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/hyperbrowser/framework/mastra-ai)
- [CrewAI](https://composio.dev/toolkits/hyperbrowser/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 Hyperbrowser
- Connect LlamaIndex to the Hyperbrowser MCP server
- Build a Hyperbrowser-powered agent using LlamaIndex
- Interact with Hyperbrowser 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 Hyperbrowser MCP server, and what's possible with it?

The Hyperbrowser MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hyperbrowser account. It provides structured and secure access to automated browser sessions, web scraping, and browser-based task management, so your agent can launch sessions, extract data, manage automation jobs, and monitor progress on your behalf.
- Automated browser session creation: Let your agent spin up new browser sessions with custom privacy, stealth, and proxy settings for tailored automation tasks.
- Scalable web scraping and extraction: Easily initiate and manage scrape jobs to extract structured content from any target website, with support for session and scrape customization.
- Real-time job status monitoring: Have your agent check, track, and report the live status of browser-use, crawl, or data extraction jobs, ensuring you always know what's happening.
- Retrieve results from automation jobs: Fetch and review the outputs of completed crawl or extract jobs, including paginated data and detailed results, right inside your workflow.
- Profile and automation management: Create or delete Hyperbrowser profiles as needed, giving you flexible control over your automation environment and resources.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `HYPERBROWSER_CREATE_PROFILE` | Create Hyperbrowser Profile | Tool to create a new profile. Use when you need to initialize a Hyperbrowser profile before analysis. |
| `HYPERBROWSER_CREATE_SCRAPE_JOB` | Create Scrape Job | Tool to initiate a new scrape job. Use when you need to extract structured content from a target URL with custom session and scrape settings. |
| `HYPERBROWSER_CREATE_SESSION` | Create Session | Tool to create a new browser session with custom stealth, proxy, and privacy settings. Use when initializing an automated browsing session with specific configuration. |
| `HYPERBROWSER_DELETE_PROFILE` | Delete Profile | Tool to delete a profile. Use when you need to remove a profile by its unique identifier after confirming its existence. |
| `HYPERBROWSER_GET_BROWSER_USE_TASK_STATUS` | Get browser-use task status | Tool to retrieve the current status of a browser-use task. Use when checking if a browser automation task has completed or is still pending. |
| `HYPERBROWSER_GET_CLAUDE_COMPUTER_USE_TASK_STATUS` | Get Claude Computer Use Task Status | Tool to retrieve the status of a Claude Computer Use task. Use after creating a task to poll its status. |
| `HYPERBROWSER_GET_CRAWL_JOB_RESULT` | Get Crawl Job Result | Tool to retrieve the result of a completed crawl job. Use after confirming crawl job completion to fetch current page batch and status. Supports pagination via page and batchSize. |
| `HYPERBROWSER_GET_CRAWL_JOB_STATUS` | Get Crawl Job Status | Tool to retrieve the status and results of a specific crawl job. Use after submitting a crawl job to check its progress or fetch results. |
| `HYPERBROWSER_GET_EXTRACT_JOB_RESULT` | Get Extract Job Result | Tool to fetch the status and results of a specific extract job. Use after initiating an extract job to monitor progress and retrieve final data. |
| `HYPERBROWSER_GET_EXTRACT_JOB_STATUS` | Get Extract Job Status | Tool to retrieve the status of an extract job. Use after submitting an extract job to poll its status. |
| `HYPERBROWSER_GET_PROFILE_BY_ID` | Get Profile By ID | Tool to retrieve profile details by ID. Use after confirming the profile ID. |
| `HYPERBROWSER_GET_SCRAPE_JOB_RESULT` | Get Scrape Job Result | Tool to fetch the status and results of a specific scrape job. Use after initiating a scrape job to monitor its progress and retrieve final data. |
| `HYPERBROWSER_GET_SCRAPE_JOB_STATUS` | Get Scrape Job Status | Tool to retrieve the current status of a specific scrape job. Use after initiating a scrape job to poll its status. |
| `HYPERBROWSER_GET_SESSION_DETAILS` | Get Session Details | Tool to retrieve session details by ID. Use after confirming the session ID. |
| `HYPERBROWSER_GET_SESSION_DOWNLOADS_URL` | Get Session Downloads URL | Tool to retrieve the downloads URL for a session. Use when you need the signed URL for session downloads after processing is complete. |
| `HYPERBROWSER_GET_SESSION_RECORDING` | Get Session Recording | Tool to retrieve the recording URL of a session. Use after confirming the session ID and when the recording is expected to be ready. |
| `HYPERBROWSER_LIST_PROFILES` | List Profiles | Tool to list profiles. Use when you need to fetch paginated profiles and optionally filter by name. |
| `HYPERBROWSER_LIST_SESSIONS` | List Sessions | Tool to list sessions with optional status filter. Use when you need a paginated overview of browser sessions before acting on them. |
| `HYPERBROWSER_START_BROWSER_USE_TASK` | Start Browser Use Task | Tool to start an asynchronous browser-use task. Use when you need to automate web interactions given a task instruction. |
| `HYPERBROWSER_START_CLAUDE_COMPUTER_USE_TASK` | Start Claude Computer Use Task | Tool to start a Claude Computer Use task. Use when you need AI-driven automated browser interactions. Call after you have your task prompt and any session preferences configured. |
| `HYPERBROWSER_START_CRAWL_JOB` | Start Crawl Job | Tool to start a new crawl job for a specified URL. Use when you need to initiate a web crawl before checking job status. |
| `HYPERBROWSER_START_EXTRACT_JOB` | Start Extract Job | Tool to start an extract job. Use when you need to initiate a new extraction with custom prompts, schema, and session options. Call after preparing URLs and desired extraction schema. |
| `HYPERBROWSER_STOP_BROWSER_USE_TASK` | Stop Browser Use Task | Tool to stop a running browser-use task. Use when halting an in-progress browser automation task after confirming its task ID. |
| `HYPERBROWSER_STOP_CLAUDE_COMPUTER_USE_TASK` | Stop Claude Computer Use Task | Tool to stop a running Claude computer use task. Use when a Claude computer use task is in progress and needs to be terminated. |
| `HYPERBROWSER_STOP_SESSION` | Stop Session | Tool to stop a running session by ID. Use after confirming the session is active. |

## Supported Triggers

None listed.

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

The Hyperbrowser MCP server is an implementation of the Model Context Protocol that connects your AI agent to Hyperbrowser. It provides structured and secure access so your agent can perform Hyperbrowser 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 Hyperbrowser account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Hyperbrowser

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 Hyperbrowser 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, hyperbrowser)
- 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 Hyperbrowser 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=["hyperbrowser"],
    )

    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 Hyperbrowser actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Hyperbrowser 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: ["hyperbrowser"],
    },
  );

  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 Hyperbrowser 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 Hyperbrowser
```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 Hyperbrowser, 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=["hyperbrowser"],
    )

    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 Hyperbrowser actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Hyperbrowser 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: ["hyperbrowser"],
    },
  );

  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 Hyperbrowser 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 Hyperbrowser to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Hyperbrowser 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 Hyperbrowser MCP Agent with another framework

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

## Related Toolkits

- [Apilio](https://composio.dev/toolkits/apilio) - Apilio is a home automation platform that lets you connect and control smart devices from different brands. It helps you build flexible automations with complex conditions, schedules, and integrations.
- [Basin](https://composio.dev/toolkits/basin) - Basin is a no-code form backend for quickly setting up reliable contact forms. It lets you collect and manage form submissions without writing any server-side code.
- [Bouncer](https://composio.dev/toolkits/bouncer) - Bouncer is an email validation platform that verifies the authenticity of email addresses in real-time and batch. It helps boost deliverability and reduce bounce rates for your communications.
- [Conveyor](https://composio.dev/toolkits/conveyor) - Conveyor is a platform that automates security reviews with a Trust Center and AI-driven questionnaire automation. It streamlines compliance and vendor security processes for faster, hassle-free reviews.
- [Crowdin](https://composio.dev/toolkits/crowdin) - Crowdin is a localization management platform that streamlines translation workflows and collaboration. It helps teams centralize multilingual content, boost productivity, and automate translation processes.
- [Databox](https://composio.dev/toolkits/databox) - Databox is a business analytics platform that connects your data from any tool and device. It helps you track KPIs, build dashboards, and discover actionable insights.
- [Detrack](https://composio.dev/toolkits/detrack) - Detrack is a delivery management platform for real-time tracking and proof of delivery. It helps businesses automate notifications and keep customers updated every step of the way.
- [Dnsfilter](https://composio.dev/toolkits/dnsfilter) - Dnsfilter is a cloud-based DNS security and content filtering solution. It helps organizations block online threats and manage safe internet access with ease.
- [Faraday](https://composio.dev/toolkits/faraday) - Faraday lets you embed AI in workflows across your stack for smarter automation. It boosts your favorite tools with actionable intelligence and seamless integration.
- [Feathery](https://composio.dev/toolkits/feathery) - Feathery is an AI-powered platform for building dynamic data intake forms with advanced logic. It helps teams automate complex workflows and collect structured data with ease.
- [Fillout forms](https://composio.dev/toolkits/fillout_forms) - Fillout forms is an online platform for building and managing forms with a flexible API. It lets you create, distribute, and collect responses from forms with ease.
- [Formdesk](https://composio.dev/toolkits/formdesk) - Formdesk is an online form builder for creating and managing professional forms. It's perfect for collecting data, automating workflows, and integrating form submissions with your favorite services.
- [Formsite](https://composio.dev/toolkits/formsite) - Formsite lets you build online forms and surveys with drag-and-drop simplicity. Capture, manage, and integrate form responses securely for streamlined workflows.
- [Graphhopper](https://composio.dev/toolkits/graphhopper) - GraphHopper is an enterprise-grade Directions API for routing, optimization, and geocoding across multiple vehicle types. It enables fast, reliable route planning and logistics automation for businesses.
- [La Growth Machine](https://composio.dev/toolkits/lagrowthmachine) - La Growth Machine automates multi-channel sales outreach and routine tasks for sales teams. Streamline your workflow and focus on closing more deals.
- [Leverly](https://composio.dev/toolkits/leverly) - Leverly is a workflow automation platform that connects and coordinates actions across your apps. It streamlines repetitive processes so your business runs smoother, faster, and with fewer manual steps.
- [Maintainx](https://composio.dev/toolkits/maintainx) - Maintainx is a cloud-based CMMS for centralizing maintenance data, communication, and workflows. It helps organizations streamline maintenance operations and improve team coordination.
- [Make](https://composio.dev/toolkits/make) - Make is an automation platform that connects your favorite apps and services. Build powerful, custom workflows without writing code.
- [Ntfy](https://composio.dev/toolkits/ntfy) - Ntfy is a notification service to send push messages to phones or desktops. Instantly deliver alerts and updates to users, devices, or teams.
- [Persona](https://composio.dev/toolkits/persona) - Persona offers identity infrastructure to automate user verification and compliance. It helps organizations securely verify users and reduce fraud risk.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Hyperbrowser MCP?

With a standalone Hyperbrowser MCP server, the agents and LLMs can only access a fixed set of Hyperbrowser tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Hyperbrowser 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 Hyperbrowser tools.

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

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

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