Stealth Agent Browser MCP server
Stealth Chromium MCP server with hybrid AOM + Set-of-Mark vision and Readability extraction.
1 stars58 downloads/wk
Reviews
Write oneNobody has reviewed Stealth Agent Browser yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Stealth Agent Browser tools (13, 1 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
browser_clickClick an element addressed by its ref. When SAB_HUMAN_MOUSE=true (default), the cursor travels via a Bezier path with pre-click hesitation — this defeats trajectory analyzers like Datadome that flag teleporting mice.
browser_evalEvaluate a JS EXPRESSION in the page's MAIN execution world. Observable by page scripts; use sparingly. Prefer AOM + action tools.
browser_navigateNavigate the active session's page to a URL. Returns a snapshot (default: aom-only, cheapest).
browser_restartClose the active browser session and start a fresh one with the current config. Required after 'browser_set_proxy' to actually route new requests through the proxy.
browser_scroll_readScroll and return a Readability-extracted Markdown view. With deltaOnly=true, returns '(no change)' if nothing new became visible — keeps context windows lean.
browser_selectSelect one or more options in a <select> addressed by ref.
browser_set_proxywrite actionUpdate the proxy config. Call 'browser_restart' after this for the change to take effect (browser-level constraint — an existing context cannot be re-routed).
browser_set_proxy_poolReplace the residential proxy pool at runtime. Takes effect on the next 'browser_restart'. Supports sticky sessions via SAB_PROXY_STICKY_TEMPLATE.
browser_snapshotTake a snapshot of the current page. 'aom' returns the accessibility YAML (token-lean); 'hybrid' adds a Set-of-Mark screenshot with numeric red boxes matching each ref.
browser_solve_captchaFallback captcha solver. Detects Turnstile/hCaptcha/reCAPTCHA on the current page (or takes an explicit sitekey), submits to the configured provider (CapSolver or 2Captcha per SAB_CAPTCHA_PROVIDER + SAB_CAPTCHA_API_KEY), polls for a token, and injects it into the widget's response field.
browser_tabsManage browser tabs: list, new, close, switch.
browser_typeType into an input or textarea addressed by ref.
browser_wait_forWait until either some text appears on the page or a given ref resolves to a visible element.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan30 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 166 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Stealth Agent Browser compares
Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 72/100
- higher than 38% of 866 Scraping and browsing servers
- Tools
- 13
- the typical Scraping and browsing server has 6
- Tools that change things
- 8%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 50% of 583 Scraping and browsing servers
- Downloads a week
- 58
- more than 40% of 309 Scraping and browsing servers with a package
What its tools let an agent do: 12 read · 1 change
Install Stealth Agent Browser in Claude Code, Cursor or VS Code
Runs npx -y stealth-agent-browser-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add stealth-agent-browser-mcp -- npx -y stealth-agent-browser-mcp
What the publisher says
From the Stealth Agent Browser repository's README, as published. We do not edit it. Read it on GitHub
stealth-agent-browser-mcp
A Model Context Protocol (MCP) server that gives AI agents a stealth-grade Chromium browser with a hybrid Accessibility-Object-Model + Set-of-Mark vision interface. Built for Claude, works with any MCP-compatible host.
- Stealth first. Uses rebrowser-playwright to patch the Runtime.Enable CDP leak that bypasses playwright-extra-class stealth plugins. Passes modern bot-detection suites (CreepJS, bot.sannysoft.com) where vanilla Playwright fails.
- Token-lean by default. browser_snapshot returns Playwright aria snapshot YAML (~2–5 KB) instead of raw HTML (100KB+). Every interactive element carries a [ref=eN] id that actions consume directly — no selectors, no drift.
- Hybrid vision when it matters. Ask for mode: "hybrid" and the server overlays numbered red boxes on the screenshot so the model can ground visually (Set-of-Mark prompting, Yang et al.). The ref ids on the image match the ids in the YAML. No parallel numbering scheme to go out of sync.
- Readability-based content extraction. browserscrollread runs Mozilla Readability through JSDOM and returns clean Markdown — optionally delta-only, so re-reads cost nothing when nothing changed.
- Proxy-ready. Per-session proxy auth, useful with residential pools.
Authorized use only. Stealth tooling has legitimate applications (accessibility auditing, your-own-account automation, QA against sites you own or have permission to test). Do not use this server to violate a site's terms of service or applicable law. See SECURITY.md.
Install
npm install -g stealth-agent-browser-mcp
# Chromium binary is fetched automatically on first launch
npx playwright-core install chromiumOr run without install via npx stealth-agent-browser-mcp.
Quickstart (Claude Desktop / Claude Code / Cursor)
Add to your MCP config:
{
"mcpServers": {
"stealth-browser": {
"command": "npx",
"args": ["-y", "stealth-agent-browser-mcp"],
"env": {
"SAB_HEADLESS": "true",
"SAB_STEALTH_LEVEL": "patched"
}
}
}
}Restart the host. The agent will see the tools listed below.
Tools
All action tools are addressed by the ref emitted in the last AOM snapshot. Refs are Playwright's own aria-ref=eN ids — there is no parallel numbering scheme.
Configuration
All via environment variables:
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Stealth Agent Browser: common questions
- Is Stealth Agent Browser MCP server safe?
- Mostly: it is graded B (72/100). Read the Stealth Agent Browser safety report
- How do I install Stealth Agent Browser?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Stealth Agent Browser need an API key?
- Yes. The registry entry asks for
SAB_PROXY_USERNAME,SAB_PROXY_PASSWORD. - Is Stealth Agent Browser maintained?
- The last commit was 204 days ago (2026-04-14). The latest release is v0.2.0.
- What can I use instead of Stealth Agent Browser?
- Servers from other publishers that do the same job: Browser Use MCP server, Ui.Vision MCP server and CloakBrowser MCP server.
- How does Stealth Agent Browser compare with other Scraping and browsing MCP servers?
- safety score 72/100 (higher than 38% of 866 Scraping and browsing servers); tools 13 (the typical Scraping and browsing server has 6); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Stealth Agent Browser
Same job from other publishers: the closest match first, then the best rated.
- Browser UseBrowser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.not reviewedEstablishedA
Ui.Vision MCPMCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard inputnot reviewedEstablishedB- CloakBrowser MCPPlaywright MCP-compatible browser automation bridge for CloakBrowser Chromium.not reviewedEstablishedB
- FortressStealth browser for AI agents: fetch pages behind Cloudflare/DataDome/CAPTCHA, extract clean data.not reviewedEstablishedB
MCP BrowserBrowser automation using the user's Chromium session — JS execution, auth, and anti-bot support.not reviewedGrowingA