BrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab., Because it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent., Require human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms., Use a test profile or non-production account for end-to-end testing and repetitive automation.
Privacy notes
Connected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model., Logged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents., Although the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
Author
BrowserMCP
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
4 safety and 3 privacy notes across 5 risk areas. Review closely: credentials & tokens, third-party handling.
5 areas
SafetyData retentionBrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab.
SafetyCredentials & tokensBecause it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent.
SafetyExecution & processesRequire human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms.
SafetyLocal filesUse a test profile or non-production account for end-to-end testing and repetitive automation.
PrivacyData retentionConnected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model.
PrivacyCredentials & tokensLogged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents.
PrivacyThird-party handlingAlthough the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
Safety notes
BrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab.
Because it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent.
Require human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms.
Use a test profile or non-production account for end-to-end testing and repetitive automation.
Privacy notes
Connected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model.
Logged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents.
Although the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
Prerequisites
Node.js installed for the MCP server.
Chrome or compatible Chromium browser.
BrowserMCP extension installed from the project site.
MCP client such as Claude, Cursor, VS Code, Windsurf, or another compatible host.
Dedicated browser profile or tab for agent automation when working with sensitive accounts.
BrowserMCP is a browser automation MCP server paired with a Chrome extension.
It lets AI applications such as Claude, Cursor, VS Code, and Windsurf automate a
connected tab in the user's existing browser profile rather than launching a
fresh browser instance.
The project emphasizes local automation, reuse of the user's current browser
profile, and workflows where an AI assistant can test web apps or automate
repetitive browser tasks.
These sources were reviewed on 2026-06-05. Prefer the live docs for current
extension installation, server config, supported clients, and troubleshooting.
Features
Chrome extension plus local MCP server package.
Setup examples for Claude, Cursor, VS Code, Windsurf, and other MCP clients.
Connected-tab automation using the user's existing browser profile.
Navigation, back/forward, wait, keyboard input, click, hover, drag and drop,
text entry, accessibility snapshots, screenshots, and console-log tools.
Local automation designed to reduce network latency.
Useful for browser task automation and end-to-end testing workflows.
Installation
Install and pin the BrowserMCP extension from the project site, then add the MCP
server to your AI application:
Open the extension, click Connect on the tab you want the agent to control, and
then issue browser automation requests through your MCP client.
Use Cases
Let an AI coding assistant run end-to-end checks against a local web app.
Automate repetitive browser tasks in a controlled profile.
Capture screenshots and accessibility snapshots for UI debugging.
Reproduce user flows that require an existing logged-in browser session.
Test form filling, navigation, and client-side behavior from an AI editor.
Safety and Privacy
BrowserMCP is convenient because it uses a real browser profile, but that also
makes it sensitive. Prefer a dedicated testing profile, keep unrelated accounts
closed, and require approval for submissions, payments, account updates, data
deletion, or communication with other people.
Treat connected-tab content, screenshots, console output, and form fields as
sensitive. They can contain personal data, credentials, customer records, or
internal application state.
Duplicate Check
content/mcp/playwright-mcp-server.mdx covers Playwright-driven browser
automation, content/mcp/chrome-devtools-mcp-server.mdx covers the official
Chrome DevTools server, and content/mcp/chrome-mcp-server.mdx covers the
separate hangwin/mcp-chrome extension bridge. This entry covers the
BrowserMCP/mcp project and its BrowserMCP extension workflow.
Show that BrowserMCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/browsermcp-server)
How it compares
BrowserMCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Chrome extension-based MCP server that exposes an existing Chrome browser profile to AI assistants for tab management, page content, screenshots, interaction, history, bookmarks, and network inspection.
Browser-control MCP server and CLI that lets AI agents use a real Chrome session, including logged-in browser state, site adapters, DOM snapshots, authenticated fetches, network traces, screenshots, and page actions.
✓BrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab.
Because it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent.
Require human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms.
Use a test profile or non-production account for end-to-end testing and repetitive automation.
✓This server controls the user's existing Chrome browser profile and can reuse logged-in sessions.
Tools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts.
Use a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them.
Do not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval.
The project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
✓bb-browser can control a real browser session, inspect pages, click elements, fill inputs, evaluate JavaScript, fetch URLs with browser authentication, capture screenshots, and inspect network traffic.
Commands may act as the logged-in user on social, finance, job, developer, shopping, and knowledge websites.
Keep the daemon bound to trusted local interfaces unless you deliberately configure remote access through a private network.
Review community site adapters before using them with authenticated accounts or valuable sessions.
Require human approval before posting, submitting forms, changing account settings, applying to jobs, making purchases, or running destructive site actions.
✓Browser pages can contain prompt-injection text in visible content, hidden HTML, ARIA labels, console output, network responses, or page metadata.
The server can navigate pages, click, hover, fill forms, drag, upload files, accept dialogs, dismiss dialogs, go through history, change viewport size, close tabs, and restart Firefox.
Enabling evaluate_script allows arbitrary JavaScript in page context; compromised instructions could read page data, modify the DOM, or interact with accessible browser APIs.
Enabling privileged context tools with the required Firefox system-access environment variable can expose privileged Firefox APIs and may extend beyond web-content sandbox boundaries.
Connect-existing mode can attach to a real browsing session with cookies, logins, active tabs, history, and saved state, so avoid it unless the profile is dedicated to automation.
Accepting insecure certificates weakens TLS validation and can hide man-in-the-middle or misconfiguration signals.
Privacy notes
✓Connected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model.
Logged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents.
Although the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
✓Open tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model.
Screenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents.
Browser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
✓Tab URLs, titles, DOM snapshots, page content, selected elements, screenshots, network requests, responses, console output, traces, and authenticated fetch results may be exposed to the MCP client and model.
Browser login state is used by the page and browser; even if cookies are not extracted directly, commands can act through authenticated sessions.
Network request bodies and response data may contain tokens, account data, personal messages, search history, customer information, or internal application data.
The upstream privacy doc says communication is local and there is no telemetry or external server, but model providers still receive any data your MCP client sends in prompts or tool results.
✓Page content, DOM snapshots, accessibility labels, console messages, network requests, headers, screenshots, uploaded file paths, extension names, Firefox prefs, and browser logs can be sent to the MCP client and model.
A regular Firefox profile can expose cookies, saved sessions, browsing history, account data, extensions, and private tabs to browser automation.
Screenshot save paths, uploaded files, downloaded artifacts, and model transcripts can reveal local project names, test data, credentials shown on pages, or customer information.
Use a separate profile, minimize enabled capabilities, avoid sensitive sites, and review provider/browser data handling before automating logged-in sessions.
Prerequisites
Node.js installed for the MCP server.
Chrome or compatible Chromium browser.
BrowserMCP extension installed from the project site.
MCP client such as Claude, Cursor, VS Code, Windsurf, or another compatible host.
Node.js 20 or newer and npm or pnpm.
Chrome or Chromium browser.
Latest Chrome MCP extension release from the project repository.
Globally installed mcp-chrome-bridge package.
Node.js 18 or newer.
Chrome session, local daemon, and Chrome extension or supported OpenClaw browser path configured according to the upstream README.
MCP client such as Claude Code, Codex, Cursor, or another compatible host.
Explicit approval to let an agent use the active browser's logged-in state.
Node.js 20.19.0 or newer.
Local Firefox 100 or newer, or an explicit Firefox binary path passed through the documented CLI option.
A dedicated Firefox automation profile with no personal cookies, saved passwords, or regular browsing sessions.
Optional adb and Firefox for Android setup when using Android automation mode.