ultrabrowse
Ultrabrowse is an MCP server that lets an AI agent delegate end-to-end web tasks to a fast, Jev-driven Chrome browser, plus inspect and manually control pages.
browse: accomplish a plain-English goal on a page (open a URL or continue current tab); returns status, steps, and final page snapshot.extract: get structured JSON from a page, optionally after browsing to it, using a schema description.browse_many: run multiple url+goal tasks in parallel tabs with configurable concurrency.snapshot: fast, key-free read of visible page text and numbered interactive elements.Manual controls:
click,type_text,press_key,scroll,backto take over or fine-tune browsing.screenshot: capture a JPEG of the current tab.close: close the current tab (plusclose_allis mentioned in the README).
Supports Brave as an alternative Chromium-based browser, providing the same automated browsing capabilities as Chrome.
Drives a real Google Chrome instance via the Chrome DevTools Protocol to automate web browsing, including clicking, typing, extracting data, and completing goals.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ultrabrowse Find the yearly price of the Pro plan on the pricing page"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ultrabrowse
Ultra-fast browsing for Claude Code, Codex, Cursor and any MCP client.
Hand your agent a goal ("find the yearly price of the Pro plan", "search for X and open the first result") and a real Chrome on your machine does the clicking, driven by TypeSafe's Jev (a small action-selection model that returns one indexed choice per call, not text) at about 300 ms per decision. Your big model makes one tool call and gets the result. It never spends tokens or seconds on the intermediate pages.
Independent open-source project; not affiliated with TypeSafe (makers of Jev) or browser-use. The engine is the jev-ultrafast policy rebuilt in plain JavaScript over raw Chrome DevTools Protocol. No Playwright, no Python, no native modules.
per step | 10-step task | what your model sees | |
Model driving a browser tool click by click | seconds | 30–90 s | every page, every step |
| ~0.3 s | 3–10 s | one result |
Install
Needs Node 22+ and Google Chrome (Chromium, Brave or Edge also work). Two API keys:
TYPESAFE_API_KEYpicks every click. Get one at https://typesafe.aiTEXT_MODEL_API_KEYis an OpenAI-compatible key used whenever text has to be typed and forextract. Default provider is OpenRouter (https://openrouter.ai/keys); any/chat/completionsendpoint works viaTEXT_MODEL_BASE_URL.
Pass them like any other MCP server, in the env block. If you prefer a file, put them in
~/.ultrabrowse/.env (template: .env.example); the env block always takes precedence.
Claude Code
claude mcp add ultrabrowse -e TYPESAFE_API_KEY=… -e TEXT_MODEL_API_KEY=… -- npx -y ultrabrowse@latestOr install the plugin, which adds the server plus a skill that teaches Claude to delegate whole web
tasks instead of clicking step by step (keys then go in ~/.ultrabrowse/.env):
/plugin marketplace add narekgevorgyan/ultrabrowse
/plugin install ultrabrowse@ultrabrowseCodex CLI
codex mcp add ultrabrowse --env TYPESAFE_API_KEY=… --env TEXT_MODEL_API_KEY=… -- npx -y ultrabrowse@latestor in ~/.codex/config.toml (raise the tool timeout: Codex defaults to 60 s and a browse can take longer):
[mcp_servers.ultrabrowse]
command = "npx"
args = ["-y", "ultrabrowse@latest"]
tool_timeout_sec = 300
[mcp_servers.ultrabrowse.env]
TYPESAFE_API_KEY = "…"
TEXT_MODEL_API_KEY = "…"Add to AGENTS.md: "For any web task, call the ultrabrowse MCP browse tool with a goal instead of driving a browser click by click."
Cursor, Windsurf, Claude Desktop
{
"mcpServers": {
"ultrabrowse": {
"command": "npx",
"args": ["-y", "ultrabrowse@latest"],
"env": { "TYPESAFE_API_KEY": "…", "TEXT_MODEL_API_KEY": "…" }
}
}
}VS Code (.vscode/mcp.json)
{
"servers": {
"ultrabrowse": {
"command": "npx",
"args": ["-y", "ultrabrowse@latest"],
"env": { "TYPESAFE_API_KEY": "…", "TEXT_MODEL_API_KEY": "…" }
}
}
}From a clone
The bundle dist/cli.cjs is committed, so a clone needs no npm install:
git clone https://github.com/narekgevorgyan/ultrabrowse
claude mcp add ultrabrowse -- node "$PWD/ultrabrowse/dist/cli.cjs"
node ultrabrowse/dist/cli.cjs doctor # checks keys and Chrome (opens a Chrome window; add --no-launch to skip)Related MCP server: jev-browser-use
Tools
Tool | What it does |
| The one to use. Opens the URL (or continues in the current tab when |
| No-model read in ~0.5 s: on-screen text (plus same-origin iframe text) and numbered elements, one line each ( |
| Browse (optional), then return JSON shaped like |
| Goal-driven runs across many sites in parallel tabs. |
| Manual control over the numbered elements, for taking over when a |
| JPEG of the current tab; close this server's tab; close every page in ultrabrowse's Chrome (tabs left by other processes too). Tabs are also closed when the MCP client disconnects. |
Chrome
By default ultrabrowse launches a dedicated Chrome with its own profile under
~/.ultrabrowse/chrome-profile and reuses it across calls, restarts and clients: Claude Code and
Codex (or several sessions) running at once all share the one Chrome; whoever starts first launches it
and the others join it. The profile persists
(cookies and logins survive), so treat it like a browser profile; rm -rf ~/.ultrabrowse/chrome-profile
resets it. Set ULTRABROWSE_HEADLESS=1 to hide the window.
To browse as yourself (logged-in sessions, internal tools), start a Chrome with remote debugging and point ultrabrowse at it:
# macOS example; a separate profile dir so it doesn't fight your everyday Chrome
"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --remote-debugging-port=9222 --user-data-dir="$HOME/.ultrabrowse/my-chrome"ULTRABROWSE_CDP_URL=http://127.0.0.1:9222What leaves your machine
api.typesafe.ai, on every step: the current page's URL, title, visible text, the labels and values of interactive elements, your goal, and the last 10 actions. No cookies, no screenshots, no password fields.
openrouter.ai (or your
TEXT_MODEL_BASE_URL), only when text has to be typed or you callextract: the goal, the schema, and up to 14 000 characters of page text.Nothing else. No telemetry, no update checks.
Safety
Model output is only ever an index into elements the page snapshot observed. It cannot produce a selector, a URL, or code that runs.
The snapshot skips
password,fileandhiddeninputs, so ultrabrowse cannot type a password.Every click is hit-tested at execution time (visible, not covered, still the same element).
Bot challenges (Cloudflare and friends) are reported as
challenge: true, never solved.Runs are bounded by an action budget, wall time, and no-progress detection.
Develop
npm install
npm run build # regenerates the inlined snapshot and bundles to dist/cli.cjs
node scripts/smoke.js dist # live end-to-end test over stdio (needs keys + Chrome)
claude plugin validate . # checks the plugin manifestssrc/snapshot.js is the in-page atomic snapshot (from jev-ultrafast, plus React-clickable divs);
src/engine.js the bounded loop; src/browser.js the CDP tab; src/model.js the TypeSafe and
text-model client; src/server.js the tools.
MIT.
Available Tools
11 toolsbackA
Go back one page in the current tab's history and return the new snapshot.
Inputs: no named parameters.
browseA
Accomplish a plain-English goal on a web page end to end: a Jev-driven Chrome picks and executes every click and field at ~300 ms per step. Pass url to open a page, or omit it to continue in the current tab. Returns status (done | blocked | stuck | budget | timeout | error), the steps taken, and the final page: url, title, visible text, numbered elements. One call replaces a whole click-by-click session. Needs TYPESAFE_API_KEY and TEXT_MODEL_API_KEY.
Inputs: goal (required), url, timeout_s, screenshot, +1 more.
browse_manyA
Run several url+goal tasks in parallel tabs and return all results (compact). Use for checking many sites or pages at once.
Inputs: tasks (required), concurrency, max_actions.
clickA
Click element [index] from the last snapshot/browse. Returns the new snapshot.
Inputs: index (required).
closeA
Close the current tab.
Inputs: no named parameters.
extractA
Get structured JSON from a page. With goal, browses there first; without it, extracts from the current page. Describe the shape in schema, e.g. '{plans:[{name, monthly_price, yearly_price}]}'.
Inputs: schema (required), url, goal.
press_keyA
Press a key in the current tab: Enter, Escape, Tab, Backspace, ArrowUp/Down/Left/Right, PageDown, Home, End, or a single character. Returns the new snapshot.
Inputs: key (required).
screenshotB
JPEG screenshot of the current tab.
Inputs: no named parameters.
scrollB
Scroll the current tab down (or up) and return the new snapshot.
Inputs: direction.
snapshotA
Fast, no-model read of a page (~0.5 s): visible text plus numbered interactive elements you can pass to click/type_text. Pass a url to open it, or omit to re-read the current tab. Needs no API keys.
Inputs: url.
type_textA
Type text into editable element [index] (replaces its content). Set submit=true to press Enter afterwards. Returns the new snapshot.
Inputs: text (required), index (required), submit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Most tools are clearly distinct: click, type_text, press_key, scroll, back, close, snapshot, screenshot, and extract each have a specific role. Some overlap exists between browse, browse_many, and extract with a goal, since all can perform autonomous browsing, but their outputs and parallelism distinguish them.
Tool names mostly follow an imperative command style with snake_case for multi-word names like type_text, press_key, and browse_many. Minor deviations like snapshot, screenshot, and back are noun/adverb-style rather than verb_ noun, but the overall pattern is readable and predictable.
11 tools is well-scoped for a browser automation server. Each tool covers a distinct aspect of browsing, reading, interacting, or tab management without excessive redundancy or an overwhelming surface.
The core browser lifecycle is well covered: navigation via browse/back, reading via snapshot/screenshot/extract, interaction via click/type_text/press_key/scroll, and tab handling via close. Minor gaps like reload or forward navigation are absent, but the high-level browse tool can work around many of those cases.
Maintenance
Related MCP Connectors
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Let AI agents use your real, signed-in Chrome: tabs, clicks, forms, screenshots and video.
Let your AI agent operate any website through a real, logged-in browser session.
Let AI agents work in your own signed-in Chrome, with approvals and verified results.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables agents to delegate browser exploration to Jev by providing natural-language objectives, receiving compact evidence and source context, and continuing the same live browser session through supervisor handoffs.61Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to control a persistent Chrome browser through a local daemon, with Jev performing routine actions and the host agent handling reasoning, text, and verification.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to drive a real Chrome browser for autonomous web tasks, using fast typed decisions with calibrated confidence, human-in-the-loop questions, safety gates, and full debug traces.7MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to drive a real headful Chrome browser using vision-first computer interactions, with support for multi-agent tab groups, password-manager-filled logins, and human handoff.10 npmMIT