Browser MCP logo

Browser MCP

Unclaimed

by Agent360dk

Drive your real, logged-in Chrome from any AI agent (Claude Code, Cursor, VS Code) — works where headless dies. Reads emailed login codes from your Gmail, solves CAPTCHAs, 34 tools. MIT, local-only.

Install

$npx @agent360/browser-mcp install

Set up this server

This server needs project-specific setup. Follow the project instructions; no reusable public launch command is available yet.

Project instructions
2faai-agentai-agentsanthropicbrowser-automationcaptchachrome-extensionclaudeclaude-codecursorlocal-firstmcpmcp-servermodel-context-protocolplaywright-alternativevscodeweb-automation

More in Search & Web

Browse the full directory

Unclaimed listing

Is this your MCP server?

This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.

Claim this server

Security profile

Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works

34 of 34 tools

Documented tools (34)

From project documentation. A server handshake does not verify each tool’s description or behavior.

browser_ask_user

Show overlay dialog for 2FA, CAPTCHA, credentials, or any user input

browser_click

Click via CSS or text selector (text=Submit, button:text(Next))

browser_close_tab

Close tab (session-owned only)

browser_console_logs

Capture console.log/warn/error messages from page

browser_dismiss_overlays

Bulk-dismiss popups/modals/tooltips/banners via aria-label/text/×-char heuristics. noncritical mode preserves dialogs with form data

browser_drop_file

Upload via drop-zones: finds hidden <input type="file"> in target subtree/parent (up to 2 levels). Use when browseruploadfile fails because the zone has no visible input

browser_execute_script

Run JavaScript in page context

browser_extract_token

Navigate to provider dashboard + extract API token

browser_fetch

HTTP request from extension (bypasses CORS)

browser_fill

Fill input fields (works on CSP-strict sites)

browser_get_cookies

Get cookies for domain

browser_get_local_storage

Read localStorage

browser_get_new_tab

Get most recently opened tab (OAuth popups)

browser_get_page_content

Get page text or HTML

browser_handle_dialog

Accept/dismiss native alert/confirm/prompt dialogs

browser_hover

Hover for tooltips/dropdowns

browser_list_frames

List iframes on page

browser_list_tabs

List session's tabs only

browser_navigate

Navigate to URL (reuses tab, or newtab=true)

browser_press_key

Keyboard events (Enter, Tab, Escape, modifiers)

browser_screenshot

Screenshot via Chrome Debugger (works even when tab isn't focused)

browser_scroll

Scroll to element or by pixels

browser_select_frame

Execute JS in specific iframe

browser_select_option

Native <select> + custom dropdowns (Angular Material, React Select)

browser_set_combobox

Autocomplete/combobox: type query → wait for filtered listbox → click option (multi-value chip support). Use when browserselectoption fails on lazy-rendered options

browser_set_cookies

Set cookies for a domain

browser_set_date

Robust date inputs: tries native value-set → masked typing → calendar-picker navigation (MUI/AntD/react-datepicker/Lexical). Use when browserfill fails on date fields

browser_set_local_storage

Write localStorage values

browser_solve_captcha

Detect and solve CAPTCHAs. Auto-detects reCAPTCHA v2/v3, hCaptcha, Turnstile, FunCaptcha. Actions: detect, clickcheckbox (auto-click, often passes when signed into Google), clickgrid (AI vision guided), askhuman (fallback)

browser_switch_tab

Switch to tab by ID

browser_upload_file

Upload files to <input type="file"> via Chrome Debugger API (no dialog)

browser_wait

Wait for element to appear

browser_wait_for_network

Wait for specific API call to complete

Human-in-the-Loop

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

No complete tool checks yet.

FAQ

Questions about Browser MCP Server

How do I connect Browser MCP Server to Claude?
The listing records `npx @agent360/browser-mcp install` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor, VS Code as compatible clients.
Is Browser MCP Server free?
The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
What can Browser MCP Server do?
Browser MCP Server documents 34 tools to the agent, including browser_ask_user, browser_click, browser_close_tab. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.