SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Browser Use MCP with Hermes

Connect Hermes to Browser Use MCP. Capture screenshots of checkout pages hourly, fill and submit job application forms, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Browser Use logoBrowser Use
Api Key

Browser Use Cloud provides hosted browser agents, managed browser sessions, workspaces, profiles, and integrations. Use it to run browser-based automations at scale with managed sessions and profiles.

39 Tools

Introduction

Hermes is a 24/7 autonomous agent that lives on your computer or server — it remembers what it learns and evolves as your usage grows.

This guide explains the easiest and most robust way to connect your Browser Use account to Hermes. You can do this through either Composio Connect CLI or Composio Connect MCP. For personal use we recommend the CLI, but you won't go wrong with MCP either.

Also integrate Browser Use with

ChatGPTClaude CoworkAtomic Agent

What is Composio Connect?

Composio Connect is a consumer offering that lets anyone plug 1,500+ applications directly into their agent harness — including Hermes. It can:

  • Search and load tools from relevant toolkits on-demand, reducing context usage.
  • Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
  • Manage app authentication end-to-end with zero manual overhead.

Integrating Browser Use with Hermes

Using Composio Connect CLI

1. Install the Composio CLI

Run the install script directly, or paste https://composio.dev/hermes into your Hermes chat box to have it installed for you.

bash
curl -fsSL https://composio.dev/install | bash
Hermes authenticating with Composio

2. Authenticate

Once the CLI is installed, ask Hermes to authenticate with Composio.

3. Connect to Browser Use

Ask your agent to connect to Browser Use, or simply request any Browser Use-related task. Hermes will prompt you to authenticate and authorize access.

4. Done. You're all set with a new Browser Use connection.

Using Composio Connect MCP

1. Get your MCP URL and API Key

Go to dashboard.composio.dev and copy your Connect MCP URL and API key.

Copy MCP URL and API key from Composio dashboard

2. Open the Hermes config file

bash
nano ~/.hermes/config.yaml

3. Add the Composio Connect MCP server

bash
mcp_servers:
  composio:
    url: "https://connect.composio.dev/mcp"
    headers:
      x-consumer-api-key: "YOUR_COMPOSIO_API_KEY"
    connect_timeout: 60
    timeout: 180

Save with Ctrl + O, Enter, then exit with Ctrl + X.

4. Restart your Hermes agent

Once restarted, ask your agent to connect to Browser Use or request any Browser Use-related task. It will prompt you to authenticate and authorize access.

5. Done!

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

The Browser Use MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Browser Use account. It provides structured and secure access so your agent can perform Browser Use operations on your behalf.

Way Forward

With Browser Use connected, Hermes can now act on your behalf whenever it detects a relevant task or you ask it to.

From here, you can extend Hermes further:

  • Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Hermes can do for you.
  • Build workflows across tools: Once multiple apps are connected, Hermes can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
  • Let it learn your patterns: The more you use Hermes, the better it gets at anticipating how you'd handle recurring tasks. Give it feedback on drafts and decisions, and it will adapt.

If you run into trouble or want to share what you've built, join the community or check out the Docs for deeper configuration options.

TOOLS

Supported Tools

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

Archive Workspace

Archive a workspace so it is no longer readable through the workspace API.

Cancel Queued Message

Cancel a queued session message while it is still pending.

Cancel Run

Idempotently cancel an in-flight browser-agent run; completed work cannot be resumed by this call.

Create Browser Session

Launch a paid managed browser for direct CDP control; time is prepaid and unused time is refunded when the browser is stopped.

Create Browser Profile

Create a persistent browser profile for reusable cookies and browser state.

Create Workspace

Create an empty workspace for browser-run input files and outputs.

Delete Browser Profile

Permanently delete a persistent browser profile and its configuration.

Delete Session

Soft-delete a conversation session and cancel its active run and pending messages.

Delete Workspace File

Permanently delete one exact relative file path from a workspace.

Disconnect Integration

Disconnect a downstream provider from the Browser Use project, revoking its availability to future runs.

Get Browser Session

Get a managed browser's status, control URLs, costs, metadata, and recording state.

Get Integration Status

Check whether one downstream integration provider is connected to the Browser Use project.

Get Browser Profile

Get one persistent browser profile's metadata and observed cookie domains.

Get Queued Message

Get one queued session message, including its terminal handoff state.

Get Run

Get a run's full result, usage, and optionally its ordered input-file attachments.

Get Run Status

Read a run's lightweight indexed status for caller-controlled polling.

Get Session

Get one conversation session's latest-run summary and busy or idle status.

Get Session Feedback

Get all feedback votes recorded for a conversation session.

Get Session Share

Get a session's current or inactive public share-link state without changing its exposure.

Get Workspace

Get workspace metadata and optionally its current storage use and plan quota.

List Browser Downloads

List one page of files downloaded by a managed browser, optionally including presigned URLs that expire after 15 minutes.

List Browser Sessions

List managed browser sessions with status, metadata, and agent-session filters, one page at a time.

List Integration Categories

List the category names used to organize Browser Use integration providers.

List Integrations

Search Browser Use integration providers and filter by popularity or project connection status, one page at a time.

List Run Payment Methods

Return AgentCard wallets and the project's active Stripe Link connection that browser runs can use for payments.

List Browser Profiles

List or search persistent browser profiles one page at a time.

List Run Events

Read one page of a run's execution events incrementally, with optional event output payloads.

List Runs

List browser-agent runs, optionally restricted to one conversation session, one page at a time.

List Session Queue

List pending and recently delivered messages for a conversation session, including transcript cutoffs created by steering interrupts.

List Sessions

List conversation sessions with each session's latest run and busy or idle status, one page at a time.

List Workspace Files

List one page of files in a workspace by path prefix, optionally including temporary download URLs.

Queue Session Message

Queue a follow-up for a conversation session, optionally interrupting its active run; dispatch may consume credits and trigger external browser work.

Set Session Feedback

Set, replace, or clear feedback for one session chat item.

Set Session Sharing

Enable or disable a session's stable public share link, creating or reactivating it when enabled.

Start Browser Run

Start an asynchronous hosted browser-agent task that may make irreversible changes on external sites and consume project credits.

Stop Browser Session

Stop a managed browser session and refund unused prepaid time subject to the one-minute minimum charge.

Update Browser Profile

Update a persistent browser profile's name, user identifier, or both.

Update Session

Rename a conversation session or explicitly clear its title.

Update Workspace

Rename a workspace or explicitly clear its name.

FRAMEWORKS

How to build Browser Use MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Browser Use MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Browser Use MCP with Claude Cowork

Atomic Agent logo

Atomic Agent

Use Browser Use MCP with Atomic Agent

FAQ

Frequently asked questions

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

Yes, you can. Hermes 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 Browser Use tools.

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

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

Start with Browser Use.It takes 30 seconds.

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

Start building