browser-use-mcp-server

MCP server · GitHub · ★ 849 · graded 2026-10-24Source linked

Browse the web, directly from Cursor etc.

No outside reports on file

This tool gives an AI direct control over your browser with access to all your logged-in accounts and personal web activity, which is high-risk unless tightly controlled and monitored.

Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Browser Use MCP Server helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachFetches arbitrary web URLsREVIEW
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (kontext-security/browser-use-mcp-server)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/kontext-security/browser-use-mcp-server ↗

All setup options ↓

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-24.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Browser Use MCP Server

This MCP server lets AI assistants like Claude browse websites and interact with web pages directly. It can click links, fill out forms, read page content, and take screenshots—essentially automating web browsing tasks from within your coding environment.

Who it’s for

Developers using Claude through Cursor or other MCP-compatible clients who want their AI to research websites, gather information, or perform web automation tasks. It's useful for testing, data collection, or automating repetitive web interactions.

Alternatives

  • Puppeteer/Playwright: Headless browser libraries you control directly in code
  • Selenium: Web automation framework for testing and data collection
  • Manual browser + Claude conversation: Have Claude guide you through steps instead of automating
  • Specialized APIs: Use official website APIs instead of browser scraping when available

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README for installation steps. The setup likely involves configuring it in your Claude Desktop or MCP client settings, which typically uses a JSON configuration block pointing to the server.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100
GitHub stars
849
Listing last refreshed
2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • Browser context access: The server can read any website content the browser visits, including sensitive information from pages you're logged into (emails, bank sites, private accounts)
  • Form hijacking: It could fill out and submit forms without your attention, potentially changing passwords, making purchases, or sending messages
  • Cookie/session theft: If the browser stores authentication cookies, the server can access authenticated sessions for any site you're logged into
  • Malicious webpage tricks: Websites can use hidden content, invisible forms, or JavaScript to trick the server into taking unintended actions
  • Data leakage to AI: Website content—including passwords, API keys, or personal data visible on pages—could be sent to Claude's servers during processing

How to lower the risk

Least-privilege permissions

  • Use a separate browser profile with minimal login sessions
  • Don't let it access banking, email, or sensitive accounts

Network isolation

  • Run it on a restricted network or container if possible
  • Limit which domains it's allowed to visit

Monitoring

  • Log all sites visited and actions taken by the server
  • Review browser history regularly for unexpected activity

Red flags to watch for

  • Server requesting access to all websites without limits
  • Prompts asking it to enter credentials or visit banking sites
  • Unusual network traffic or slow performance
  • Requests to disable monitoring or logging

Questions

How do I install Browser Use MCP Server?

Browser Use MCP Server does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/kontext-security/browser-use-mcp-server.

Are there security reports about Browser Use MCP Server?

No reports found for this package in our research (last checked 2026-10-30). Browser Use MCP Server currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include browser context access, form hijacking, cookie/session theft.

Is Browser Use MCP Server actively maintained?

Browser Use MCP Server has 849 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/kontext-security/browser-use-mcp-server before pinning it in production.

What are alternatives to Browser Use MCP Server?

Notable alternatives to Browser Use MCP Server include Puppeteer/Playwright (Headless browser libraries you control directly in code), Selenium (Web automation framework for testing and data collection), Manual browser + Claude conversation (Have Claude guide you through steps instead of automating), Specialized APIs (Use official website APIs instead of browser scraping when available). You can also compare Browser Use MCP Server side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use Browser Use MCP Server? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade C for Browser Use MCP Server

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for Browser Use MCP Server](https://agentarmorhq.com/api/badge/kontext-security-browser-use-mcp-server)](https://agentarmorhq.com/skills/kontext-security-browser-use-mcp-server)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/kontext-security-browser-use-mcp-server"><img src="https://agentarmorhq.com/api/badge/kontext-security-browser-use-mcp-server" alt="AgentArmorHQ Risk Grade for Browser Use MCP Server" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "kontext-security-browser-use-mcp-server"

Share with your security lead

Need sign-off to use browser-use-mcp-server? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: browser-use-mcp-server
- **Listing URL:** https://agentarmorhq.com/skills/kontext-security-browser-use-mcp-server
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 849 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Fetches arbitrary web URLs
- **Credentials:** No API token required
- **Package source:** GitHub (kontext-security/browser-use-mcp-server)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/kontext-security/browser-use-mcp-server
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 24, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
kontext-security
Source code
github.com/kontext-security/browser-use-mcp-server
Est. context load
~650 tokens / turn (~4 tool schemas, 0.33% of 200k context)
Popularity
849 GitHub stars
Last updated
2026-10-29
Last graded
2026-10-24

Community

Discussions for Browser Use MCP Server

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Browser Use MCP Server helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude