real-browser-mcp-server
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 0 of 1 tool tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y real-browser-mcp-server@3.3.17
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
1 tool that takes no input and looks read-only was called once with nothing. 0 returned a result.
get_content | No usable answer tool reported an error: { "error": "browserType.launch: Executable doesn't exist at /tmp/.cache/ms-playwright/chromium-1248/chrome-linux64/chrome\n╔══════════ |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
browser_init headless, proxy, contextOptions, widgetAssist, enableBlocker, aiHealing, recordVideo, spoofFingerprint, blockWebRTCLeaks, fingerprint
Initialize a browser session with configurable options: headless mode, proxy, viewport, video recording, resource filtering, biometric anti-detection hardware spoofing (WebGL, Canvas, AudioContext), and WebRTC leak protection. Automatically recovers stale sessions.
navigate url, tabAction, tabIndex, autoSwitchNewTab, waitUntil, timeout, retries, smartWait, waitForChallenge, challengeTimeout, challengePollInterval
Navigate to a URL or manage browser tabs (list, switch, new tab, close tab). Supports configurable wait conditions, timeout, automatic retry on failure, and waitForChallenge to auto-solve Cloudflare-style JS challenges.
get_content format, selector, xpath, text, waitForJS, timeout, extractAttributes, multiple, includeMeta, saveAs, rawHttpUrl
Get page content in multiple formats: html, text, markdown, rawHttp, or elements. Extracts text, attributes, or bounding box coordinates. Can save directly to a file.
wait type, value, timeout
Wait for a selector, navigation event, networkidle state, or a fixed timeout before continuing.
click selector, annotationId, dragTo, humanLike, aiHeal, autoAcceptDialogs, retries, clickCount, delay, timeout, hoverFirst, hoverOnly, hoverDuration, iframe, iframeSelector, scrollIntoView, forceClick, autoDetectPlayer, usePlayerAPI, waitForPlay, playerTimeout
Click or drag a page element by CSS selector or annotation ID. Supports drag-and-drop / slider manipulation via dragTo, iframe context, hover before click, video player API, and automatic retry with fallback selectors.
14 more tools
type selector, annotationId, text, delay, clear, aiHeal, iframe, iframeSelector, pressEnter, waitForSelector
Type text into an input field with configurable keystroke delay, field clearing, and iframe support.
browser_close force
Close the browser session and release all browser resources.
solve_captcha type, timeout, captchaSelector, widgetSelector, inputSelector, refreshSelector, lang, expectedLength, allowedChars, maxRetries, iframe, iframeSelector, formData, formSelector, submit, humanLike, aiMatch, analyzeFirst, preferTextFallback
Automate form completion and interactive widget verification on web pages. Supports JavaScript-based challenge widgets, image text transcription, and intelligent form field mapping for QA and automated browsing workflows.
random_scroll direction, amount, smooth, aiDetectLazyLoad, iframe, iframeSelector
Scroll the page with configurable direction, amount, and automatic lazy-load triggering.
redirect_tracer url, maxRedirects, includeHeaders, followJS, followMeta, decodeURLs, timeout
Trace the complete redirect chain of a URL. Tracks HTTP 301/302, JavaScript navigation (window.location, setTimeout), and meta refresh tags. Returns the full path with status codes and headers.
extract_data type, types, pattern, selector, jsonPath, source, autoDecode, flags, inputData, autoDetectKey, transformKey, keyOffset, includeHidden, searchIframes
Extract structured data from the current page in multiple modes: regex, json, meta, structured, auto, apiDiscovery, parse (string conversion), transform (data format conversion), or links (all links including nested iframes).
press_key key, modifiers, count, humanDelay
Press keyboard keys with configurable modifier keys, repeat count, and keystroke delay.
deep_analysis detailed, aiInsights, detectAccessControls
Inspect the current page in depth: DOM structure, scripts, stylesheets, accessibility, performance metrics, SEO tags, response headers, loaded technologies, and content-loading strategy recommendations.
network_recorder action, filter, patterns, mock, aiDetectStreams, captureXhrBody, limit, offset
Record, inspect, and control network activity. Supports 14 actions: start, stop, get, clear, get_media, get_navigations, get_api_calls, get_intercepted_apis, get_websockets, get_graphql, export_har, block_urls (block images/trackers to boost speed 3x-5x), mock_route (intercept & mock API responses), clear_routes.
media_extractor action, types, quality, deep, searchIframes, selector, index, playerAction, encodedData, decoderType, decoderKey, decoderIV, urls, async, aiOptimize
Extract and control media from the current page. Supports 6 actions: extract (find video/audio/HLS/DASH/download URLs including nested iframes), list_iframes, switch_iframe, player_control (play/pause/seek/sources via player API), decode_url (inspect converted string and token formats), batch_extract.
execute_js code, action, url, method, headers, body, returnValue, async, timeout, iframe, iframeSelector, waitForIframe
Execute custom JavaScript in the page context with async support, return value capture, and iframe targeting. Also supports action="fetch" to replay HTTP requests with the page session (cookies/auth inherited, 30s timeout, structured status/headers/body output).
storage_inspector action, sessionPath, passphrase, enabled
Inspect and manage client-side storage & sessions. Supports 7 actions: cookies (get all current cookies), save_session (persist cookies & storage state to file), load_session (restore state from file without re-logging), clear_cookies, autosave (auto-save session on every navigation), indexeddb, service_workers.
see_page annotate, fullPage, format, quality, includeElements, includeDomText, includePageText, scanIframes, maxElements, async, path, autoHover, watchMutations, steps, captureBefore, captureAfter, stopOnError, saveBaseline, compareBaseline
Capture a snapshot of the current page. Returns a screenshot image together with optional full-page text, an interactive element map (buttons, links, inputs with position and selector), and an iframe inventory — all in a single call. Workflow: Call once with fullPage:true and annotate:true. From that snapshot, run all planned actions (click, type, scroll, wait, extract) as a steps array without re-capturing the page. Call see_page again only when the page genuinely changes (new navigation, modal, or dynamic content load).
async_job action, jobId
Poll or cancel background jobs started with async:true on media_extractor batch_extract, see_page steps, or execute_js. Read-only except cancel.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | ISC |
|---|---|
| Needs | node >=24.0.0 |
| Source | not stated |
| Install scripts | real-browser-mcp-server declare them. This runner does not run them. |
| Tarball | sha512-5+5sH+R7HFKNv4xt3CAwevIdI9F2WsaNvOiqEmcogkj7H/n6zBdXhxjS19EOPPgk9HVWZ0WG53dd5f794v/o1Q== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/real-browser-mcp-server)
New version out? Ask for a fresh report.