browser MCP server
Commit Oct 25, 2026Provides a hosted Chromium browser that allows AI agents to navigate websites, click elements, type text, and take screenshots with persistent user sessions.
Also known as globalion/browser-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.2.0
- Last commit
- Oct 25, 2026
- License
- MIT
What is browser MCP?
browser provides a hosted Chromium browser that allows AI agents to navigate websites, click elements, type text, and take screenshots with persistent user sessions.
Summary generated from the project's README
About browser MCP server
Giving AI agents the ability to interact with the live web is what browser-mcp enables. By providing a hosted Chromium instance via Playwright, this server allows clients like Claude Desktop or Cursor to navigate websites, click elements, type text, and capture screenshots. It operates as a remote service where you connect via an API key in your configuration, allowing your agent to act as the brain while the server handles the browser driving.
Security is a central focus, especially when dealing with login-gated websites. The server uses AES-256-GCM to encrypt credentials at rest, and the use_credentials tool allows the agent to log into sites without the LLM ever seeing the actual password. Each user receives an isolated BrowserContext to ensure cookies and local storage remain private. Sessions are managed through tools like browser_new_session and browser_snapshot, with an automatic 15 minute idle timeout to manage resources.
What you can do with it
- 1Automated web navigationAsk your AI agent to go to a specific website and search for information.
- 2Securely accessing private accountsLog into websites using stored credentials that the LLM cannot read.
Written from the project's README. Every use case is checked against a quote from it.
How to install browser MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall browser MCP in Claude Code
$ claude mcp add --transport http browser-mcp https://browser.regiq.in/api/mcpInstall browser MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"browser-mcp": {
"url": "https://browser.regiq.in/api/mcp"
}
}
}Install browser MCP in VS Code
.vscode/mcp.json
{
"servers": {
"browser-mcp": {
"type": "http",
"url": "https://browser.regiq.in/api/mcp"
}
}
}Install browser MCP in VS Code CLI
$ code --add-mcp '{"name":"browser-mcp","type":"http","url":"https://browser.regiq.in/api/mcp"}'Install browser MCP in Codex
$ codex mcp add browser-mcp --url https://browser.regiq.in/api/mcpInstall browser MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.browser-mcp] url = "https://browser.regiq.in/api/mcp"
Install browser MCP in Gemini CLI
$ gemini mcp add -s user --transport http browser-mcp https://browser.regiq.in/api/mcpInstall browser MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"browser-mcp": {
"url": "https://browser.regiq.in/api/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableglobalion/browser-mcp is public and reachablegithub.com/globalion/browser-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-25github.com/globalion/browser-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 208 msPass
README
View on GitHubbrowser-mcp
Hosted Chrome as an MCP skill. Give any MCP-compatible agent (Claude Desktop, Cursor, custom scripts) a real Chromium browser to drive — navigate, click, type, snapshot, read pages, take screenshots. Human-like behaviour, per-user isolated sessions, encrypted credential storage so login-gated sites work without leaking passwords to the LLM.
- Real Chromium on our server via Playwright. Not headless-only tricks — full browser context.
- Stealth defaults — patches the most common bot-detection tells (navigator.webdriver, plugins, chrome runtime). Not bulletproof against heavy defences like Cloudflare Turnstile; v0.2 adds proxies + CAPTCHA solving.
- Per-user isolation — separate BrowserContext per user, so cookies + localStorage don't leak between accounts.
- Encrypted credentials — AES-256-GCM at rest.
use_credentialstypes the password into the page server-side; the LLM never sees it. - No LLM in our stack — your agent is the brain. We just drive the browser.
Hosted at browser.regiq.in.
Use it
-
Visit https://browser.regiq.in and sign in with Google or GitHub.
-
Generate an MCP API key on the dashboard.
-
Add to Claude Desktop's
claude_desktop_config.json:{ "mcpServers": { "browser": { "url": "https://browser.regiq.in/api/mcp", "headers": { "Authorization": "Bearer YOUR_KEY_HERE" } } } } -
Restart Claude Desktop. Ask it: "open workit.info and search for placements in Cambridge." Your agent will call the browser tools and drive the page.
Tools
| Tool | Purpose |
|---|---|
browser_new_session() |
Spin up a session; returns sessionId. 15 min idle timeout. |
browser_close_session(sessionId) |
Clean up. |
browser_navigate(sessionId, url) |
Go to URL, wait for DOMContentLoaded. |
browser_snapshot(sessionId) |
Accessibility tree with per-element uids. |
browser_click(sessionId, uid) |
Click element by uid. |
browser_type(sessionId, uid, text) |
Fill input by uid. |
browser_press_key(sessionId, key) |
Keyboard press: Enter, Tab, Control+A, etc. |
browser_wait_for(sessionId, selector) |
Wait for CSS selector to appear. |
browser_read_page(sessionId) |
Plain-text page content (20 KB cap). |
browser_screenshot(sessionId) |
PNG as base64. |
save_credentials(domain, username, password) |
Encrypt + store login for a site. |
use_credentials(sessionId, domain, usernameSelector, passwordSelector) |
Type stored creds into a login form. Password never returned. |
list_saved_credentials() |
See what's stored (domains + usernames only). |
Handling login-gated sites
Your agent sees a login form. Flow:
- Check for saved creds —
list_saved_credentials(). - If saved for this domain — call
use_credentials(sessionId, "workit.info", "input[name=email]", "input[type=password]"). Server decrypts + types. Then click the submit button. - If not saved — tell the user: "I need your workit.info login to continue. Save it at https://browser.regiq.in/dashboard, then ask me again."
For MVP the user has to save creds via the dashboard. v0.2 will let the agent request creds through a paired channel (e.g. via telegram-mcp).
Self-host
You'll need:
- Docker + Compose
- A Google or GitHub OAuth client
- A public HTTPS domain (Cloudflare Tunnel or
ngrok http 3013) - ~4 GB RAM (Playwright + Chromium)
git clone https://github.com/globalion/browser-mcp
cd browser-mcp
cp .env.example .env
# fill NEXTAUTH_SECRET, GOOGLE_/GITHUB_*, PUBLIC_BASE_URL,
# and generate CRED_ENCRYPTION_KEY with `openssl rand -hex 32`
docker compose up -d
# open http://localhost:3013
Architecture
Your MCP agent → /api/mcp (Bearer auth) → In-memory session Map → Playwright BrowserContext
↕
Postgres (audit + credentials, AES-256-GCM)
Sessions live in the container's memory. A restart kills all active sessions — users just call browser_new_session again. Contexts auto-close after 15 min idle to free RAM.
Bot avoidance — realistic expectations
The stealth init script strips navigator.webdriver, adds fake plugins, exposes window.chrome.runtime, and patches the notifications permission oddity. Combined with a real Chromium binary (not headless-only) and realistic viewport/UA/timezone, that gets past most public sites.
Sites with serious anti-bot (Cloudflare Turnstile, PerimeterX, DataDome) will still detect. To bypass those you need:
- Residential proxies (~$50/mo services like Bright Data)
- CAPTCHA solving (~$0.001/solve via 2captcha)
- More elaborate fingerprint spoofing
That's v0.2 territory. For now, use browser-mcp on sites that aren't actively hunting bots.
License
MIT.
browser MCP questions
How do I add browser MCP to Claude Code?
Run claude mcp add --transport http browser-mcp https://browser.regiq.in/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add browser MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can the AI see my passwords when logging into websites?
No, passwords are encrypted using AES-256-GCM and typed into the page server-side so the LLM never sees them.
Does this server work against heavy bot detection like Cloudflare?
It includes stealth defaults to patch common bot-detection tells, but it is not bulletproof against heavy defenses like Cloudflare Turnstile.
How long do browser sessions last?
Sessions have a 15-minute idle timeout.