ZenLink MCP
Leverages Zen Browser (Firefox-based) as the automation target, providing full browser control including tab management, network interception, session persistence, and Readability extraction.
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., "@ZenLink MCP Navigate to example.com and extract the markdown content"
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.
ZenLink MCP
MCP server for browser automation via ZenLink — gives Claude Desktop and other MCP clients native browser control through Zen Browser (Firefox-based).
v2.0.0 ships ~50 new tools for parallel agentic work: real multi-tab parallelism, tab unloader defense, session save/restore, Readability + Markdown extraction, request interception, cookies/storage, and orchestration primitives (broadcast, sync barriers, tab pools, named tags). See CHANGELOG.md for the full list.
Installation
pip install zenlink-mcpRelated MCP server: Browser Agent MCP Server
Requirements
ZenLink browser extension v2.0.0+ installed in Zen Browser
ZenLink bridge running (
python native/bridge.py)
Tool surface (75+ tools)
Every tab-aware tool below accepts an optional tab_id parameter — pass it to drive a specific tab without stealing focus, the foundation for parallel multi-tab work.
Core
zen_status, zen_health, zen_tabs, zen_new_tab, zen_close_tab, zen_switch_tab, zen_navigate, zen_screenshot
Content extraction (read once, work cheaply)
zen_page_text, zen_page_info, zen_readability, zen_markdown, zen_query, zen_html, zen_links, zen_images, zen_meta, zen_structured_data, zen_bounds, zen_computed_style, zen_dom, zen_forms, zen_iframes, zen_explain_selector, zen_full_page_metrics
Interaction
zen_click, zen_trusted_click, zen_double_click, zen_type, zen_fill, zen_form_fill, zen_set_editable_content, zen_select_option, zen_check, zen_focus, zen_blur, zen_keypress, zen_submit_form, zen_drag, zen_hover, zen_scroll, zen_find, zen_highlight, zen_click_and_wait_navigation
Visual
zen_screenshot, zen_element_screenshot, zen_full_page_screenshot
Tab and window management
zen_pin_tab, zen_mute_tab, zen_duplicate_tab, zen_reload_tab, zen_back, zen_forward, zen_get_zoom, zen_set_zoom, zen_windows, zen_create_window, zen_close_window, zen_focus_window, zen_move_tab, zen_detach_tab
Network, cookies, state
zen_cookies, zen_storage (local/session), zen_clipboard, zen_downloads, zen_clear_browsing_data, zen_intercept, zen_capture_network, zen_wait_for_network_idle, zen_wait_for_url, zen_wait_for_title, zen_watch_console, zen_console_logs
Sessions (auth-once-use-many)
zen_save_session, zen_load_session, zen_list_sessions, zen_delete_session
Orchestration (parallel multi-tab)
zen_keep_alive, zen_keep_alive_stop, zen_wake_tab, zen_broadcast, zen_sync_barrier, zen_tag_tab, zen_resolve_tag, zen_list_tags, zen_untag_tab, zen_tab_pool, zen_pool_acquire, zen_pool_release, zen_parallel
Batch / scripting
zen_batch (with parallel, if, while, try, sequence, retry, ${$N.field} variable substitution)
Observability / policy
zen_logs, zen_audit, zen_set_policy, zen_get_policy, zen_retry, zen_reload_extension
Wait primitives
zen_wait_for_element, zen_wait_for_result, zen_wait_for_url, zen_wait_for_title, zen_wait_for_network_idle
Workflow
zen_workflows, zen_workflow, zen_cache, zen_wp_html
zen_wait_for_element
Waits for a CSS selector to appear and become visible on the page. Returns immediately when found rather than sleeping a fixed duration — use this instead of sleep when waiting for dynamic/JS-rendered content.
{"action": "waitForElement", "selector": ".tracking-events", "timeout": 10000}Parameter | Type | Default | Description |
| string | required | CSS selector to wait for |
| int | 10000 | Max wait time in milliseconds |
| int | 200 | How often to check in milliseconds |
Returns { ok: true, found: true, elapsed: 342, ref: "r12", tag: "div" } on success, or { ok: false, found: false, error: "Timed out after 10000ms" } on timeout.
zen_batch
Run multiple commands in one request. Supports all actions including waitForElement, trustedClick, and sleep:
[
{"action": "navigate", "url": "https://example.com"},
{"action": "waitForElement", "selector": ".results", "timeout": 8000},
{"action": "pageText"}
]Claude Desktop Setup
Add to your claude_desktop_config.json:
{
"mcpServers": {
"zenlink": {
"command": "zenlink-mcp"
}
}
}Changelog
See CHANGELOG.md for the full history. Highlights of v2.0.0:
~50 new MCP tools across content extraction, interaction, network, sessions, orchestration
Real parallel multi-tab work via
zen_parallel+zen_keep_aliveSession save/restore for auth-once-use-many flows
zen_interceptto block analytics/ads (3–10× page speedup in agent runs)zen_readability+zen_markdownfor token-efficient page extractionHot reload via
zen_reload_extension
Links
mcp-name: io.github.JayQuan-McCleary/zenlink-mcp
Available Tools
104 toolszen_auditA
Return recent command audit entries: action, params (JS code stripped), success flag, error, duration. Useful for "what did the agent do?" reviews.
Inputs: limit, since_ms.
zen_backC
Go back in history (browser back button).
Inputs: tab_id.
zen_batchA
Run multiple commands in a single request for speed.
Each command is a dict with "action" and parameters. Add "tabId" to any command to target a specific tab instead of the active one. For true concurrency across tabs, prefer zen_parallel.
Available actions: navigate, newTab, closeTab, switchTab, click, type, setEditableContent, fill, scroll, hover, find, js, pageInfo, pageText, screenshot, tabs, forms, dom, sleep, waitForElement, pageTextByTabId, wakeTab, parallel
Args: commands: List of command dicts, e.g. [{"action": "navigate", "url": "..."}, {"action": "waitForElement", "selector": ".results", "timeout": 10000}, {"action": "pageText"}]
Inputs: commands (required).
zen_blurB
Blur an element (or document.activeElement if no selector).
Inputs: selector, tab_id.
zen_boundsB
Return getBoundingClientRect + viewport/page sizes for an element.
Inputs: selector (required), tab_id.
zen_broadcastA
Fire the same command at every listed tab in parallel.
Each tab gets the command with its own tabId injected. Returns per-tab results keyed by tab id.
Args: tab_ids: Tabs to target. command: Command dict, e.g. {"action": "pageInfo"} or {"action": "getReadability"}. timeout: Per-tab timeout in seconds.
Inputs: tab_ids (required), command (required), timeout.
zen_cacheB
Control the ZenLink bridge response cache.
Args: action: "clear", "status", or "ttl" seconds: TTL value when action is "ttl"
Inputs: action, seconds.
zen_capture_networkB
Capture network requests via the page's PerformanceObserver.
Args: op: "start" begins capturing fresh, "stop" pauses, "read" returns the buffer (default), "clear" empties it. since: When reading, only return entries with startTime >= since (ms). tab_id: Optional tab; defaults to active.
Inputs: op, since, tab_id.
zen_checkC
Set a checkbox or radio's checked state.
Inputs: selector (required), checked, tab_id.
zen_clear_browsing_dataA
Clear browsing data of the given types.
Args: types: Which to clear. Subset of ["cache","cookies","history", "localStorage","passwords","downloads"]. Default = all of those. since_ms: Only data created since this epoch-ms timestamp.
Inputs: types, since_ms.
zen_clickB
Click an element on the page by CSS selector or coordinates.
Args: selector: CSS selector to click (e.g. "#submit", ".btn-primary") x: X coordinate (used if selector is empty) y: Y coordinate (used if selector is empty) tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector, x, y, tab_id.
zen_clipboardA
Read or write the system clipboard.
Args: op: "read" or "write". text: Text to write when op="write".
Inputs: op (required), text.
zen_close_tabB
Close a browser tab by its ID.
Args: tab_id: The tab ID to close (get IDs from zen_tabs)
Inputs: tab_id (required).
zen_close_windowA
Close a browser window by ID (from zen_windows).
Inputs: window_id (required).
zen_computed_styleC
Return computed CSS for an element. Defaults to the layout-relevant set.
Inputs: selector (required), properties, tab_id.
zen_console_logsA
Return buffered console logs from a tab (requires zen_watch_console first).
Inputs: since, level, tab_id.
zen_cookiesA
Cookie operations: "get", "set", "remove", "clear".
get: returns matching cookies (use url/domain/name to filter).
set: requires url + name + value.
remove: requires url + name.
clear: clears all cookies for url or domain.
Inputs: op (required), url, name, value, +3 more.
zen_create_windowA
Open a new browser window. Pass a URL to load it at start.
Inputs: url, incognito.
zen_delete_sessionC
Delete a saved session file.
Inputs: name (required).
zen_detach_tabC
Pop a tab out into its own new window.
Inputs: tab_id (required).
zen_domA
Get the accessibility tree of interactive elements on the page.
Args: tab_id: Optional tab to target. Defaults to active tab.
Inputs: tab_id.
zen_double_clickC
Dispatch a synthetic double-click on the matched element.
Inputs: selector (required), tab_id.
zen_downloadsB
Downloads operations.
Args: op: "download" | "list" | "cancel". url: For "download", the URL to fetch. filename: Optional output filename. query: For "list", a downloads.search query dict.
Inputs: op (required), url, filename, query.
zen_dragC
Synthetic drag-and-drop from one element to another (HTML5 drag events).
Inputs: from_selector (required), to_selector (required), tab_id.
zen_duplicate_tabB
Duplicate a tab. Returns the new tab id.
Inputs: tab_id.
zen_element_screenshotA
Screenshot a single element. Scrolls into view, captures, crops in the extension via OffscreenCanvas. Returns a PNG data URL.
Inputs: selector (required), tab_id.
zen_explain_selectorA
Diagnose a CSS selector: match count, sample matches, suggestions for a more-specific selector if you got too many.
Inputs: selector (required), tab_id.
zen_fillA
Set a form field's value directly (faster than typing).
Args: selector: CSS selector of the input/select element value: Value to set tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), value (required), tab_id.
zen_findA
Find elements on the page using natural language description.
Args: query: What to find (e.g. "login button", "search bar", "email input") tab_id: Optional tab to target. Defaults to active tab.
Inputs: query (required), tab_id.
zen_focusC
Move focus to the matched element.
Inputs: selector (required), tab_id.
zen_focus_windowC
Bring a browser window to the foreground.
Inputs: window_id (required).
zen_form_fillA
Fill many fields at once via fuzzy matching.
Each key in fields is matched as: CSS selector → name attribute →
label text (case-insensitive contains) → placeholder. Each value is
applied via the appropriate setter (.value for inputs/textareas, .checked
for checkboxes/radios, value for selects). Returns per-key results.
Args: fields: {"email": "foo@bar", "Password": "...", "#submit-target": true}
Inputs: fields (required), tab_id.
zen_formsB
Get all form fields on the current page with their labels and values.
Args: tab_id: Optional tab to target. Defaults to active tab.
Inputs: tab_id.
zen_forwardC
Go forward in history.
Inputs: tab_id.
zen_full_page_metricsC
Return document/viewport sizes + scroll position + devicePixelRatio.
Inputs: tab_id.
zen_full_page_screenshotB
Scroll-and-stitch screenshot covering the full document height (up to 30 viewports tall). Returns one PNG data URL of the entire page.
Inputs: tab_id.
zen_get_policyA
Return the active URL/readonly policy.
Inputs: no named parameters.
zen_get_zoomC
Return the current zoom factor (1.0 = 100%).
Inputs: tab_id.
zen_healthB
Extended health/status: bridge version, ports, keep-alive list, pool state, tags, policy, sessions dir, audit/log sizes.
Inputs: no named parameters.
zen_highlightA
Highlight an element on the page with a visual overlay.
Args: selector: CSS selector of the element to highlight tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), tab_id.
zen_hoverA
Hover over an element on the page.
Args: selector: CSS selector of the element to hover over tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), tab_id.
zen_htmlB
Return the outerHTML of a specific element. Cap 100KB.
Inputs: selector (required), tab_id.
zen_iframesC
List all iframes with src + same-origin/accessible flags.
Inputs: tab_id.
zen_imagesC
Return every with src, alt, and natural dimensions.
Inputs: tab_id.
zen_interceptA
Block, log, or redirect HTTP requests by URL regex.
Useful to suppress analytics/ads during agent runs (3–10× page speed-up) or to log what an SPA actually fetches.
Args: op: "add" | "clear" | "list" | "log" | "clearLog". patterns: For "add", regex patterns to match against request URLs. effect: For "add", "block" (cancel request) or "redirect".
Inputs: op (required), patterns, effect.
zen_jsB
Execute JavaScript in the current page context.
Args: code: JavaScript code to run (e.g. "document.title" or "document.querySelectorAll('a').length") tab_id: Optional tab to target. Defaults to active tab.
Inputs: code (required), tab_id.
zen_keep_aliveA
Keep tabs warm so Zen's Tab Unloader won't discard them mid-workflow.
Starts a background pinger in the bridge that fires a no-op JS evaluation at each listed tab on the given interval. Any script access resets Zen's idle timer, so the tabs stay loaded. Replaces any existing keep-alive for the same tabs (use a new interval to change cadence).
Use this at the start of parallel multi-tab work: open your tabs, call zen_keep_alive with their IDs, drive them in parallel via zen_parallel or by passing tab_id to individual commands, then zen_keep_alive_stop when done. The pinger auto-stops if the bridge restarts.
Args: tab_ids: Tab IDs to keep loaded. interval_seconds: How often to ping each tab. Minimum 10s, default 60s. Should be well under Zen's unloader timeout (commonly 20+ minutes).
Inputs: tab_ids (required), interval_seconds.
zen_keep_alive_stopA
Stop the keep-alive pinger for some or all tabs.
Args: tab_ids: Tabs to stop pinging. Omit (or pass null) to stop all.
Inputs: tab_ids.
zen_keypressA
Dispatch a synthetic keyboard event. Use modifiers like
{"ctrl": True, "shift": True}. Pass text to also insert characters
into editable targets.
Args: key: Key name, e.g. "Enter", "Tab", "Escape", "ArrowDown", "a". selector: Optional element to target. Defaults to document.activeElement. modifiers: {"ctrl"|"shift"|"alt"|"meta": True}. text: If set, also insert this text into editable targets.
Inputs: key (required), selector, modifiers, text, +1 more.
zen_linksB
Return every anchor with href + text. Useful as a crawler primitive.
Inputs: internal_only, tab_id.
zen_list_sessionsB
List saved sessions with their metadata.
Inputs: no named parameters.
zen_list_tagsB
List all tag → tab id mappings.
Inputs: no named parameters.
zen_load_sessionA
Restore cookies + localStorage from a previously saved session.
Inputs: name (required).
zen_logsB
Return recent bridge log lines (in-memory ring buffer).
Inputs: limit, since.
zen_markdownC
Convert the page (or a selector subtree) to Markdown. Cap 80KB.
Inputs: selector, tab_id.
zen_metaC
Return all meta tags + link rels (canonical, RSS, icons, etc.).
Inputs: tab_id.
zen_move_tabB
Move a tab to a position (and optionally to a different window). -1 = end.
Inputs: tab_id (required), window_id, index.
zen_mute_tabC
Mute or unmute a tab.
Inputs: muted, tab_id.
zen_new_tabB
Open a new browser tab.
Args: url: URL to open in the new tab (default: blank page)
Inputs: url.
zen_page_infoA
Get current page URL, title, dimensions, and scroll position.
Args: tab_id: Optional tab to target. Defaults to active tab.
Inputs: tab_id.
zen_page_textA
Extract all readable text from the current page.
Args: tab_id: Optional tab to target. Defaults to active tab. For non-active tabs, prefer this with tab_id over zen_page_text_by_tab_id — they do the same thing now.
Inputs: tab_id.
zen_page_text_by_tab_idA
Get page text from a specific tab by ID without switching to it.
Args: tab_id: The tab ID to read from (get IDs from zen_tabs)
Returns the full visible text content of the specified tab.
Inputs: tab_id (required).
zen_parallelA
Run command sequences in parallel — typically one sequence per tab.
Each inner list is a sequence that runs serially; all sequences run concurrently. Commands that target a specific tab (navigate, switchTab, or any tab-aware action) MUST include "tabId" inside the parallel batch to avoid race conditions over the active tab.
Returns a list of result lists, one per input sequence.
Args: sequences: List of command sequences. Each command is a dict with "action" and parameters — same shape as zen_batch commands. Example for driving two tabs at once: [ [{"action": "navigate", "url": "...", "tabId": 12}, {"action": "waitForElement", "selector": "h1", "tabId": 12}, {"action": "pageText", "tabId": 12}], [{"action": "navigate", "url": "...", "tabId": 13}, {"action": "waitForElement", "selector": "h1", "tabId": 13}, {"action": "pageText", "tabId": 13}] ]
Inputs: sequences (required).
zen_pin_tabC
Pin or unpin a tab.
Inputs: pinned, tab_id.
zen_pool_acquireA
Check out a warm tab from the pool. Returns its tab_id.
Inputs: no named parameters.
zen_pool_releaseC
Return a tab to the pool for reuse.
Inputs: tab_id (required).
zen_queryA
Extract multiple fields from every element matching a CSS selector.
Much faster and cheaper than calling zen_js per element. The default
fields cover the common ones (text, href, value, src, alt, id, name);
pass fields=["text","data-foo","bounds","attrs"] to get arbitrary
attributes or bounds/attrs/html extras.
Args: selector: CSS selector. fields: Field names to extract per element. Defaults to a useful set. limit: Max elements to return (capped at 500). tab_id: Optional tab; defaults to active.
Inputs: selector (required), fields, limit, tab_id.
zen_readabilityA
Extract the main article on the page (title, byline, clean text).
Heuristic: score candidate containers (article, main, .post, etc.)
by text density × paragraph count × inverse link density, strip nav/aside,
return the winner. Falls back to densest section/div, then body.
Inputs: tab_id.
zen_reload_extensionA
Hot-reload the ZenLink extension in the browser.
Use this after editing the extension source to pick up changes without
going through about:addons and toggling the extension by hand. The
extension acks the request, then reloads itself ~100ms later; the
background script's existing reconnect logic re-establishes the bridge
WebSocket immediately. Content scripts in open tabs survive — they re-
inject lazily on the next command (see forwardToContent in background.js).
Note: only works once you're already on a version of the extension that has this action handler. The very first install of that version requires the usual about:addons toggle.
Inputs: no named parameters.
zen_reload_tabA
Reload a tab. Pass bypass_cache=True for a hard reload.
Inputs: bypass_cache, tab_id.
zen_resolve_tagC
Look up the tab id for a tag set via zen_tag_tab.
Inputs: name (required).
zen_retryA
Wrap any command in exponential-backoff retry.
Args: command: A command dict (same shape as zen_batch entries). max_attempts: Total tries including the first. backoff_ms: Initial wait between attempts (doubles each retry). on_errors: Only retry if the error string contains one of these substrings. Default: retry on any error.
Inputs: command (required), max_attempts, backoff_ms, on_errors.
zen_save_sessionA
Snapshot cookies (and per-origin localStorage if urls given) to disk.
Use case: log into a service interactively once, save the session, then have parallel agents load it for authenticated work.
Args: name: A label for the session (becomes filename under ~/claude-zen-sessions/). urls: Origins whose cookies + localStorage to snapshot. Each gets opened briefly in a temp tab so localStorage can be read.
Inputs: name (required), urls.
zen_screenshotA
Capture a screenshot of the current page. Returns the saved file path.
Note: screenshots are inherently visual and capture the active tab of the focused window. To screenshot a specific tab, switch to it first with zen_switch_tab.
Inputs: no named parameters.
zen_scrollB
Scroll the page.
Args: direction: Scroll direction - "up", "down", "left", or "right" amount: Pixels to scroll tab_id: Optional tab to target. Defaults to active tab.
Inputs: direction, amount, tab_id.
zen_select_optionB
Choose an in a . Default matches by value; pass
by_text=True to match by visible text.
Inputs: selector (required), value (required), by_text, tab_id.
zen_set_editable_contentA
Set text or HTML in a contenteditable editor, input, or textarea in one fast operation.
Use this for rich editors such as Gmail compose bodies where typing long text is slow.
Args: selector: CSS selector or ZenLink ref for the editable element value: Text or HTML to place into the editor format: "text" for plain text or "html" for trusted HTML clear: Whether to replace existing content instead of appending tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), value (required), format, clear, +1 more.
zen_set_policyA
Set URL allow/deny regex lists and/or read-only mode.
Read-only mode blocks write actions (click/type/navigate/cookies set/etc.) while still allowing read ops. Useful for "let the agent observe only."
Inputs: allow, deny, readonly.
zen_set_zoomB
Set zoom factor. 0.3 to 5.0 typical; 1.0 = 100%.
Inputs: factor (required), tab_id.
zen_statusA
Check if ZenLink bridge and browser extension are connected.
Inputs: no named parameters.
zen_storageA
localStorage / sessionStorage ops.
Args: kind: "local" or "session". op: "get" | "set" | "remove" | "clear" | "list" | "snapshot" | "restore". key: Required for get/set/remove. value: For set, the string value. For restore, a dict of key→value. tab_id: Tab to run against. Storage is per-origin, so prefer driving it on a tab already at the right origin.
Inputs: kind (required), op (required), key, value, +1 more.
zen_structured_dataC
Extract JSON-LD blocks, OpenGraph (og:*), and Twitter card meta.
Inputs: tab_id.
zen_submit_formA
Submit a form. If selector is omitted, submits the first found.
Inputs: selector, tab_id.
zen_switch_tabA
Switch focus to a specific browser tab.
Args: tab_id: The tab ID to focus (get IDs from zen_tabs)
Inputs: tab_id (required).
zen_sync_barrierA
Block until a JS predicate returns truthy on every listed tab.
Replaces hand-rolled "wait for everything to be ready" loops.
Args: tab_ids: Tabs to monitor. predicate: JS expression that returns truthy when the tab is ready, e.g. "!!document.querySelector('.results')". timeout: Overall timeout in ms. poll_interval: Per-poll interval in ms.
Inputs: tab_ids (required), predicate (required), timeout, poll_interval.
zen_tab_poolA
Maintain a warm pool of N tabs always ready to be acquired.
Grows or shrinks to size. Acquire/release via zen_pool_acquire and
zen_pool_release. Auto-grows by one if you acquire from an empty pool.
Inputs: size (required), url.
zen_tabsA
List all open browser tabs with their IDs, titles, and URLs.
Inputs: no named parameters.
zen_tag_tabA
Give a tab a memorable name. Refer to it later via zen_resolve_tag. Names survive bridge restarts only if you re-tag — they live in memory.
Inputs: name (required), tab_id (required).
zen_trusted_clickA
Click using the real OS mouse pointer for pages that reject synthetic DOM events.
This is slower and moves the user's cursor, so prefer zen_click unless a page specifically ignores synthetic clicks.
Args: selector: CSS selector to click. If provided, ZenLink clicks its center. x: X coordinate, used if selector is empty. y: Y coordinate, used if selector is empty. coordinate_space: "viewport" for browser viewport coords or "screen" for desktop coords. focus: Whether to try to foreground the browser first. Defaults to false. tab_id: Optional tab to resolve the selector against (viewport coords only).
Inputs: selector, x, y, coordinate_space, +2 more.
zen_typeB
Type text into an input field.
Args: selector: CSS selector of the input element text: Text to type clear: Whether to clear existing text first tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), text (required), clear, tab_id.
zen_untag_tabC
Remove a tag.
Inputs: name (required).
zen_wait_for_elementA
Wait for a CSS selector to appear and become visible on the page. Returns immediately when the element is found, rather than sleeping a fixed duration. Use this instead of sleep when waiting for dynamic/JS-rendered content.
Args: selector: CSS selector to wait for (e.g. ".tracking-events", "#results", "[data-loaded]") timeout: Maximum time to wait in milliseconds (default: 10000 = 10s) poll_interval: How often to check in milliseconds (default: 200ms) tab_id: Optional tab to target. Defaults to active tab.
Inputs: selector (required), timeout, poll_interval, tab_id.
zen_wait_for_network_idleC
Wait until no new network resources have started for idle_ms.
Inputs: idle_ms, timeout, tab_id.
zen_wait_for_resultA
Poll a JavaScript expression until it returns a non-empty result.
Args: code: JavaScript expression to evaluate repeatedly timeout: Maximum time to wait in milliseconds poll_interval: How often to check in milliseconds tab_id: Optional tab to target. Defaults to active tab.
Inputs: code (required), timeout, poll_interval, tab_id.
zen_wait_for_titleC
Wait until document.title matches a JS regex pattern.
Inputs: pattern (required), timeout, tab_id.
zen_wait_for_urlC
Wait until the tab's URL matches a JS regex pattern.
Inputs: pattern (required), timeout, tab_id.
zen_wake_tabA
Revive a tab that Zen's Tab Unloader may have discarded.
Zen aggressively unloads inactive tabs to save RAM. An unloaded tab still appears in zen_tabs but has no live content script — commands targeting it will hang or fail until it's reloaded. zen_wake_tab is idempotent: if the tab is already alive it returns immediately; otherwise it reloads the tab and waits for the page to finish loading.
Use before targeting a tab that might have been idle for a while. Prefer zen_keep_alive for tabs you'll touch repeatedly.
Args: tab_id: The tab ID to wake (get IDs from zen_tabs)
Inputs: tab_id (required).
zen_watch_consoleA
Toggle console capture on a tab. Once enabled, browser console messages (log/info/warn/error/debug + window errors) are buffered up to 500 entries; retrieve via zen_console_logs.
Inputs: enabled, tab_id.
zen_windowsA
List all open browser windows with their tabs.
Inputs: no named parameters.
zen_workflowB
Execute a named ZenLink workflow from the bridge workflow directory.
Args: name: Workflow file name without .md variables: Optional template variables for the workflow
Inputs: name (required), variables.
zen_workflowsA
List available named ZenLink workflows from the bridge workflow directory.
Inputs: no named parameters.
zen_wp_htmlA
Extract HTML widget content from a WordPress Elementor page.
Navigates to the Elementor editor for the given page, waits for load, then extracts the innerHTML of all HTML widgets from the Elementor preview iframe. Returns clean HTML/CSS/JS content.
The browser must already be logged into WP admin for this to work.
Args: site_url: WordPress site URL (e.g. "https://thankyouexperiences.com") page_id: WordPress page/post ID (e.g. 5719 for Team page)
Inputs: site_url (required), page_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 104 tools
Most tools have clearly distinct purposes, but there is some overlap among page content extraction tools (e.g., zen_page_text, zen_markdown, zen_readability) and command batching tools (zen_batch, zen_parallel, zen_broadcast). Detailed descriptions help differentiate them.
All tools follow the 'zen_' prefix with snake_case naming, predominantly using a verb_noun pattern (e.g., zen_click, zen_navigate, zen_wait_for_element). A few noun-only names (zen_tabs, zen_windows) fit the resource-listing pattern. Consistency is excellent.
With 104 tools, the count is very high for a browser automation server. Many tools are composite or highly specialized (e.g., zen_wp_html, zen_reload_extension), which adds complexity. A more streamlined set of ~30-50 core tools would improve coherence.
The tool set covers virtually all browser automation needs: navigation, element interaction, network capture, console logs, cookies, storage, tabs, windows, screenshots, and advanced features like keep-alive and sync barriers. No significant gaps are apparent.
Maintenance
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Browz hosted MCP (free public beta): let an AI app drive your own Browz browser profiles from anywhere. Connect https://mcp.gobrowz.com/mcp and sign in with your Browz account (OAuth) or an agent token. Each call is relayed to the Browz app on your computer, which must be online with Remote control on and have a hardware security chip (Mac Secure Enclave or TPM 2.0). 17 tools: profiles, tabs, navigate, snapshot, act, wait, screenshot. Cookies, downloads and stored sign-ins stay on your computer.
Cloud browser, web extraction, screenshots, and remote CDP tools for AI agents.
Cloud browsers for AI agents: saved logins, residential IPs, live human takeover, 57 browser tools.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables browser automation through the Claude Chrome Extension, allowing agents to navigate websites, fill forms, take screenshots, and debug web apps via standard MCP protocols.1MIT
- FlicenseNot gradedqualityDmaintenanceProvides browser automation capabilities through Claude Desktop and other MCP clients, enabling navigation, screenshot capture, content extraction, and interactive control.-
- AlicenseAqualityAmaintenanceAn MCP server that enables Claude Desktop and Claude Code to drive a running Zen Browser over WebDriver BiDi, letting Claude list, open, switch, and close tabs, navigate pages, read page content, click, type, scroll, take screenshots, and extract text from a live browser session.26142 PyPI11MIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code to control a real browser for navigation, interaction, screenshots, accessibility snapshots, and automated end-to-end testing through MCP tools.106 npmMIT