# How to integrate Hyperbrowser MCP with Atomic Agent

```json
{
  "title": "How to integrate Hyperbrowser MCP with Atomic Agent",
  "toolkit": "Hyperbrowser",
  "toolkit_slug": "hyperbrowser",
  "framework": "Atomic Agent",
  "framework_slug": "atomic-agent",
  "url": "https://composio.dev/toolkits/hyperbrowser/framework/atomic-agent",
  "markdown_url": "https://composio.dev/toolkits/hyperbrowser/framework/atomic-agent.md",
  "updated_at": "2026-08-11T13:10:54.475Z"
}
```

## Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,500+ apps through Composio, including Hyperbrowser.
This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a Hyperbrowser account. See the [Atomic Agent documentation](https://atomicagent.io/docs/?cta_placement=atomic-agent-docs) for installation instructions.

## 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)
- [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)
- [LlamaIndex](https://composio.dev/toolkits/hyperbrowser/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/hyperbrowser/framework/crew-ai)
- [Pydantic AI](https://composio.dev/toolkits/hyperbrowser/framework/pydantic-ai)
- [AutoGen](https://composio.dev/toolkits/hyperbrowser/framework/autogen)

## TL;DR

### How Atomic Agent connects to Hyperbrowser
Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.
Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

## Connect Hyperbrowser to Atomic Agent

### Connect Hyperbrowser to Atomic Agent
- Sign up or sign in to the [Composio dashboard](https://dashboard.composio.dev/?cta_placement=atomic-agent-api-key). Copy your API key.
- In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
- Ask Atomic Agent to do something in Hyperbrowser. It searches Composio for the right tool.
- On first use, open the sign-in link returned in the chat. Connect your Hyperbrowser account, then return to Atomic Agent to continue.
### Headless setup
Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

```bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY
```

## 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_ADD_EXTENSION` | Add Extension | Tool to add a new browser extension to Hyperbrowser for use in sessions. Use when you need to upload a Chrome extension zip file that can be loaded into browser sessions. The extension zip must contain a valid manifest.json file at the root level. |
| `HYPERBROWSER_CREATE_PROFILE` | Create Hyperbrowser Profile | Creates a new persistent Hyperbrowser profile for storing browser state (cookies, sessions, etc.). Use this to create a reusable profile that can be attached to browser sessions via the profile ID. Profiles allow you to maintain logged-in states across multiple sessions without re-authenticating. |
| `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_FETCH_WEB_PAGE` | Fetch Web Page | Tool to fetch a web page and return content in various formats (HTML, Markdown, JSON, screenshot, etc.). Use when you need to retrieve and process web content with customizable browser settings, output formats, and content filtering options. |
| `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_RESULT` | Get Claude Computer Use Task Result | Tool to retrieve the complete result and status of a Claude Computer Use task. Use when you need full task details including execution steps, final results, and error information. |
| `HYPERBROWSER_GET_CLAUDE_COMPUTER_USE_TASK_STATUS` | Get Claude Computer Use Task Status | Poll the execution status of a Claude Computer Use task. Use after calling HYPERBROWSER_START_CLAUDE_COMPUTER_USE_TASK to check if the task has completed, is still running, or has failed. Pass the jobId returned from the start task action. |
| `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_CRAWL_STATUS` | Get Crawl Status | Tool to retrieve the current status of a specific crawl job. Use after initiating a crawl job to poll its status. |
| `HYPERBROWSER_GET_CUA_TASK_RESULT` | Get CUA Task Result | Tool to retrieve the status and results of a CUA (Claude User Agent) task. Use after starting a CUA task to check its progress, retrieve execution steps, and obtain the final result. |
| `HYPERBROWSER_GET_CUA_TASK_STATUS` | Get CUA Task Status | Poll the execution status of a CUA task. Use to check if a CUA task has completed, is still running, or has failed. |
| `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 | Retrieve the status of an extract job. Use after calling Start Extract Job to poll its progress. Poll periodically until status is 'completed' or 'failed', then use Get Extract Job Result to retrieve the extracted data. |
| `HYPERBROWSER_GET_GEMINI_COMPUTER_USE_TASK_RESULT` | Get Gemini Computer Use task result | Tool to retrieve the current status and results of a Gemini Computer Use task. Use when checking if a Gemini automation task has completed or is still pending. |
| `HYPERBROWSER_GET_HYPER_AGENT_TASK_RESULT` | Get HyperAgent Task Result | Tool to retrieve the status and results of a HyperAgent task. Use when checking if a HyperAgent task has completed or to get the final results and execution steps. |
| `HYPERBROWSER_GET_PROFILE` | Get Profile By ID | Retrieves details of a specific Hyperbrowser profile by its UUID. Returns profile metadata including name, team association, and timestamps. Use the List Profiles action first to obtain valid profile IDs. |
| `HYPERBROWSER_GET_SCRAPE_JOB_RESULT` | Get Scrape Job Result | Retrieves the status and results of a scrape job. Poll this endpoint after creating a scrape job to check progress and get the scraped content when completed. Returns jobId, status (pending/running/completed/failed), scraped data, and any error message. |
| `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; poll at moderate intervals (e.g., every 2–5 seconds) rather than tight loops to avoid exhausting quota. Responses may be large when the job includes screenshots or full HTML. |
| `HYPERBROWSER_GET_SESSION_DETAILS` | Get Session Details | Retrieve detailed information about a Hyperbrowser session by its ID. Use this tool to get connection endpoints (wsEndpoint, liveUrl), session status, and configuration details for an existing session. The session ID can be obtained from create_session or list_sessions actions. Returns active connection details (wsEndpoint, liveUrl, token) for active sessions, or historical information for closed sessions. |
| `HYPERBROWSER_GET_SESSION_DOWNLOADS_URL` | Get Session Downloads URL | Tool to retrieve the downloads URL for a session. Returns a signed URL to download files saved during a browser session. Note: The session must be created with 'saveDownloads: true' for downloads to be available. Poll this endpoint checking status until 'completed'. |
| `HYPERBROWSER_GET_SESSION_RECORDING` | Get Session Recording | Retrieve the recording URL for a browser session. Returns a pre-signed S3 URL to download the rrweb JSON recording. The recording status indicates availability: - 'pending': Recording is being prepared - 'in_progress': Recording is still being processed - 'completed': Recording is ready, recordingUrl will contain the download link - 'failed': Recording failed, check the error field - 'not_enabled': Session was created without enableWebRecording=true Poll this endpoint until status is 'completed' or 'failed' after stopping a session. |
| `HYPERBROWSER_GET_SESSION_VIDEO_RECORDING_URL` | Get Session Video Recording URL | Tool to retrieve the video recording URL for a browser session. Returns a pre-signed URL to download the video recording. The video recording status indicates availability: - 'pending': Video recording is being prepared - 'in_progress': Video recording is still being processed - 'completed': Video recording is ready, recordingUrl will contain the download link - 'failed': Video recording failed, check the error field - 'not_enabled': Session was created without enableVideoWebRecording=true Poll this endpoint until status is 'completed' or 'failed' after stopping a session. |
| `HYPERBROWSER_GET_WEB_CRAWL_RESULT` | Get Web Crawl Result | Tool to retrieve the status and results of a web crawl job. Use after submitting a web crawl job to check its progress and fetch paginated results. Supports pagination via page and batchSize parameters for large crawl jobs. |
| `HYPERBROWSER_GET_WEB_CRAWL_STATUS` | Get Web Crawl Status | Tool to retrieve just the status of a web crawl job without the full results. Use after initiating a web crawl to poll its current state. |
| `HYPERBROWSER_LIST_EXTENSIONS` | List Extensions | Tool to list all browser extensions. Use when you need to fetch all available extensions for the Hyperbrowser account. |
| `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_SEARCH_WEB` | Search Web | Tool to perform a web search and retrieve results with titles, URLs, and descriptions. Use when you need to search the web for information on a specific topic or query. |
| `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_CUA_TASK` | Start CUA Task | Tool to start an OpenAI CUA (Computer-Using Agent) task. Use when you need AI-driven automated browser interactions powered by OpenAI. Call after you have your task prompt and any session preferences configured. |
| `HYPERBROWSER_START_EXTRACT_JOB` | Start Extract Job | Start an AI-powered data extraction job from one or more web pages. Use this tool to scrape structured data from websites by providing URLs and either a natural language prompt describing what to extract, or a JSON schema defining the output structure (or both for best results). Returns a jobId to track extraction progress via HYPERBROWSER_GET_EXTRACT_JOB_STATUS and retrieve results via HYPERBROWSER_GET_EXTRACT_JOB_RESULT. |
| `HYPERBROWSER_START_GEMINI_COMPUTER_USE_TASK` | Start Gemini Computer Use Task | Tool to start a Gemini Computer Use task for browser automation using Google's Gemini. Use when you need AI-driven automated browser interactions with Gemini models. |
| `HYPERBROWSER_START_WEB_CRAWL` | Start Web Crawl | Tool to start an asynchronous web crawl job that follows links from a starting URL and returns content from each page. Use when you need to crawl multiple pages from a website. |
| `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_CUA_TASK` | Stop CUA Task | Tool to stop a running CUA task. Use when a CUA task is in progress and needs to be terminated. |
| `HYPERBROWSER_STOP_GEMINI_COMPUTER_USE_TASK` | Stop Gemini Computer Use Task | Tool to stop a running Gemini computer use task. Use when a Gemini 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.

## Troubleshooting

### Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

### Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

### Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See [Composio pricing](/pricing) for the current limits that apply to your connection.

## Complete Code

None listed.

## Conclusion

### Use Hyperbrowser from Atomic Agent
With your account connected, ask Atomic Agent to work with Hyperbrowser in natural language. You can connect more apps through the same Composio integration as you need them.
Visit the [Atomic Agent website](https://atomicagent.io/?cta_placement=atomic-agent-site) or inspect the [Atomic Agent source code](https://github.com/AtomicBot-ai/atomic-agent?cta_placement=atomic-agent-repo).

## 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)
- [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)
- [LlamaIndex](https://composio.dev/toolkits/hyperbrowser/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/hyperbrowser/framework/crew-ai)
- [Pydantic AI](https://composio.dev/toolkits/hyperbrowser/framework/pydantic-ai)
- [AutoGen](https://composio.dev/toolkits/hyperbrowser/framework/autogen)

## Related Toolkits

- [0CodeKit](https://composio.dev/toolkits/0codekit) - 0CodeKit is a utility API platform for AI, document, image, and data workflows. Use it to convert, validate, generate, store, and automate data without custom backend code.
- [Airtop](https://composio.dev/toolkits/airtop) - Airtop is a cloud browser platform for AI-powered web automation. Use it to navigate sites, extract data, and run reusable browser workflows.
- [Apify MCP](https://composio.dev/toolkits/apify_mcp) - Apify MCP is the official MCP server for Apify's web scraping and browser automation platform. Use it to run actors, collect structured web data, and automate crawling workflows.
- [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.
- [Bika.ai](https://composio.dev/toolkits/bika) - Bika.ai is an AI automation database platform for managing spaces, teams, records, automations, and outgoing webhooks. It helps teams organize structured data and automate database-driven workflows in one place.
- [Botster](https://composio.dev/toolkits/botster) - Botster is a web automation service for running configurable data collection bots. Use it to collect structured web data without building and maintaining scrapers yourself.
- [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.
- [BrowserAct](https://composio.dev/toolkits/browseract) - BrowserAct is a hosted browser-automation service for running web workflows. Use it to execute repeatable browser tasks with templates, proxies, and APIs.
- [Celigo](https://composio.dev/toolkits/celigo) - Celigo is an integration platform as a service for connecting apps, data, and business workflows. It helps teams automate cross-system processes without building every integration from scratch.
- [CheckFlow](https://composio.dev/toolkits/checkflow) - CheckFlow is a workflow and checklist platform for repeatable processes, tasks, templates, teams, data sets, and automation. Use it to standardize operations, track process execution, and keep teams aligned.
- [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.
- [Cronfree Time Scheduler](https://composio.dev/toolkits/cronfree_time_scheduler) - Cronfree Time Scheduler is an API-based scheduler for recurring webhook calls. Use it to create and remove timezone-aware schedules without running cron.
- [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.
- [Dify](https://composio.dev/toolkits/dify) - Dify is a platform for running and managing published workflow apps via a Service API. Use it to execute workflows and inspect configuration and run history quickly.
- [Digital Humani](https://composio.dev/toolkits/digital_humani) - Digital Humani is a reforestation API for browsing planting projects, submitting tree requests, and tracking planted trees. It helps teams connect climate action directly to products, campaigns, and customer experiences.
- [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.
- [EnforcedFlow](https://composio.dev/toolkits/enforcedflow) - EnforcedFlow is a work routing platform for advanced round-robin groups, agent criteria, availability, and email assignments. It helps teams distribute work fairly and quickly using configurable assignment rules.

## 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 Atomic Agent?

Yes, you can. Atomic Agent 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)