Log inSubmit server
Browser Agent logo

Browser Agent

Runs AI-directed Chrome browser tasks through an MCP server and local extension, with optional saved files and screenshots.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Browser Agent

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "browser-agent": {
      "command": "npx",
      "args": [
        "-y",
        "runbook-ai-mcp@latest"
      ],
      "env": {
        "RUNBOOK_AI_MCP_TOKEN": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y runbook-ai-mcp@latest

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 11d ago.

Overview

Run AI-directed browser tasks in Chrome with the browser-agent MCP server, which connects an MCP client to a local Chrome extension. A single MCP tool accepts a natural-language prompt and can navigate, click, type, inspect pages, and save files through the live browser session. Use it for websites without dedicated MCP integrations or for multi-step browser workflows where condensed page context is useful.

Use cases

  • Automate searches and form interactions on websites
  • Collect multi-page website data into files
  • Download reports or datasets through Chrome
  • Continue a browser workflow across multiple tool calls

Key features

  • AI-directed Chrome automation
  • Single natural-language browser task tool
  • Condensed page context
  • Persistent or isolated browser sessions
  • File and screenshot output
  • Optional MCP token authentication

Tools1

What Browser Agent lets your agent do. Expand a tool for its parameters.

Self-reported~20 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

11/11 checks healthy over the last 61d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · runbook-ai-mcp@latest (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars3Stargazers on the source repository.
npm downloads213Package downloads in the last 30 days.
Last commit20d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed1Callable tools this server registers over MCP.

How Browser Agent works

What browser-agent MCP server does

The browser-agent MCP server lets an MCP client ask an AI agent to complete tasks in a live Chrome browser. It uses a Chrome extension to perform actions such as navigation, clicking, typing, page inspection, and other browser automation steps. The extension can work with websites that do not provide a dedicated MCP integration, including public sites, account pages, and internal web tools.

The server exposes one MCP tool, browser-agent. Its required prompt describes the task in ordinary language. The tool can return task results while placing generated files, downloads, extracted datasets, screenshots, or captured payloads on the machine running the MCP server. File paths, MIME types, and sizes are listed in the result instead of placing file contents directly in the MCP response.

How it works

The MCP client communicates with the local server over stdio. When the tool is called, the server forwards the request over a WebSocket connection on port 9003 to the Runbook AI Chrome extension. The extension runs the browser task and sends the result back through the server.

Chrome must be open with the extension side panel available. The extension generates a reduced representation of page HTML that keeps relevant text and interaction elements while omitting much of the surrounding markup. This representation can include content beyond the current viewport, which supports scrolling and multi-page tasks without returning the complete DOM after every action.

Each call is isolated by default: it starts in a fresh blank tab and closes tabs opened during the run. Set ephemeral to false when later calls should continue from the previous browser state and leave the final page open. maxIterations controls the maximum number of agent actions, while effort selects quick, normal, or thorough exploration.

Setup and configuration

Install the MCP package through an MCP client configuration using npx -y runbook-ai-mcp@latest. Install the Runbook AI extension from the Chrome Web Store, open its settings, and enable MCP. The extension also requires an LLM API key, model name, and base URL; these values are configured in the extension rather than as MCP server environment variables.

The extension accepts connections on localhost:9003. Without a token, any program able to open a WebSocket to that port can drive the browser. Generate an MCP token in the extension settings and pass it with the server's --token argument to restrict requests. The server also accepts RUNBOOK_AI_MCP_TOKEN when the argument is not supplied; this avoids exposing the token in process listings on shared machines. An empty token disables the check.

By default, the extension can access all websites. Chrome's extension details can be used to restrict access to selected sites. The browser-agent MCP server does not itself make remote calls except to the LLM provider selected in the extension configuration.

Tools and capabilities

  • Run one natural-language browser task with the browser-agent tool.
  • Set an iteration limit with maxIterations; longer workflows require more iterations and token budget.
  • Choose quick, normal, or thorough exploration with effort.
  • Preserve or isolate browser state with ephemeral.
  • Write files to a chosen outputDir, or use the default temporary location.
  • Return paths for saved files and show images up to 4 MB inline as MCP image content.

The server fits the Browser Automation category when an agent needs to operate a website through Chrome rather than call a site-specific API.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Browser Agent

browser-agent is an MCP server that connects MCP clients to the Runbook AI Chrome extension and exposes a browser-agent tool for AI-directed Chrome tasks. It accepts natural-language prompts, performs navigation and other browser actions, and can return results or save downloads, datasets, screenshots, and captured files to disk.

Install it through an MCP configuration with `npx -y runbook-ai-mcp@latest`, then install the Runbook AI Chrome extension and enable MCP in its settings. Keep Chrome and the extension side panel open when the MCP client invokes the tool.

Generate an MCP token in the extension settings and pass it with `--token`, or set `RUNBOOK_AI_MCP_TOKEN` when launching the server. Requests with a missing or incorrect token are rejected; an empty token in the extension turns token checking off.

Yes, browser-agent can write files produced during a task to `outputDir` or its default temporary directory. Ask the agent to save the data, and the result will list the resulting absolute paths rather than embedding bulk file contents.

Yes, the README provides a Claude Code setup command for adding the server with `claude mcp add`. Claude Code communicates with the server over stdio while the server connects to the Chrome extension over WebSocket.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBrowser Agent AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/browser-agent?style=directory)](https://allmcps.com/mcp/browser-agent)
HTML Embed
<a href="https://allmcps.com/mcp/browser-agent"><img src="https://allmcps.com/api/badge/browser-agent?style=directory" alt="Browser Agent on AllMCPs" /></a>