# io.github.IGELHARINE/cdpm (npm · cdpm-mcp) Lets many Claude Code sessions and subagents share numbered, logged-in Chrome instances over CDP - Trust score: 68/100 (medium) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-11-04 ## Components - npm · `cdpm-mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/igelharine-cdpm/cdpm-mcp.md), [page](https://verifymcp.io/servers/igelharine-cdpm/cdpm-mcp) ## Channel facts - Registry: `npm` - Package: `cdpm-mcp` - Version: `0.1.9` - Transport: `stdio` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-11-04. - **Supply Chain Security**: 81/100 - No malware found by supply-chain analysis. - CVE check failed: a known high-severity CVE affects zod 4.6.5, a direct dependency. A fixed version is available. - No install/post-install scripts declared. - 30 of 114 dependencies flagged as unhealthy. - **Provenance & Transparency**: 45/100 - Source repository is publicly reachable at the declared URL. - Provenance check failed: no build-provenance attestation is published. - Clear OSI-approved license (MIT). - Actively maintained (last published 17 days ago). - Disclosure check failed: no security disclosure policy was found in the source repository. - **Schema Quality & AI Usability**: 58/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 11607 tokens (~322/item across 36 items; 36 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 60/100 - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 98/100 - 97% of tools have a non-trivial description (not blank, and not just the tool's name). - 99% of tool parameters carry a description. - **Tool Safety**: 75/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "browser_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. - An AI judge read all 37 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the io.github.IGELHARINE/cdpm MCP server? io.github.IGELHARINE/cdpm runs locally as an npm package, launched with npx -y cdpm-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add igelharine-cdpm -- npx -y cdpm-mcp ``` ### Cursor ```json { "mcpServers": { "igelharine-cdpm": { "command": "npx", "args": [ "-y", "cdpm-mcp" ] } } } ``` ### VS Code ```json { "servers": { "igelharine-cdpm": { "command": "npx", "args": [ "-y", "cdpm-mcp" ] } } } ``` ### Codex ```bash codex mcp add igelharine-cdpm -- npx -y cdpm-mcp ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "igelharine-cdpm": { "type": "local", "command": [ "npx", "-y", "cdpm-mcp" ], "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add igelharine-cdpm --command npx --arg -y --arg cdpm-mcp ``` ### Hermes ```yaml mcp_servers: igelharine-cdpm: command: "npx" args: ["-y", "cdpm-mcp"] ``` ### Netclaw ```json { "McpServers": { "igelharine-cdpm": { "Transport": "stdio", "Command": "npx", "Arguments": [ "-y", "cdpm-mcp" ] } } } ``` ### Vellum ```bash assistant mcp add igelharine-cdpm -t stdio -c npx -a -y cdpm-mcp ``` ### Other ```json { "mcpServers": { "igelharine-cdpm": { "command": "npx", "args": [ "-y", "cdpm-mcp" ] } } } ``` ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-11-02 (score 68, +1) No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-31 (score 67, +1) - [functional regression] Security disclosure: unverified → fail ### 2026-10-29 (score 66, +1) - [functional regression] Security disclosure: fail → unverified ### 2026-10-27 (score 65, +1) No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-25 (score 64, +1) No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-10-24 (score 63, −5) - [security regression] CVE-2023-54404 affects this package: high - [security regression] Known CVEs: pass → fail ### 2026-10-22 (score 68, +3) - [functional improvement] Stability: unverified → 0.17 ### 2026-10-18 (score 65, +15) - [security improvement] Malware scan: unverified → pass ## MCP tools (36) ### `browser_status` (~114 tokens) Slot status Shows running Chrome slots (1-30) with their tabs, opener, last action and one-line summary. Pass slot for just that slot. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. ### `browser_launch` (~520 tokens) Launch slot Starts slot Chrome. Call only when the user explicitly asks (other tools never start a closed slot). Without slot, uses the lowest free slot. If already running, just attaches. The user decides windowed (visible) vs headless (hidden): headless: true only if they say "headless/hidden". If unstated, don't guess; ask first, then call with headless. Starting a closed slot without headless only returns a confirmation request. Start several slots at once with slots (list) or count (lowest first). For different jobs per slot, after launching give each slot its own subagent in parallel. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `count` (integer): When the user gives only a count ("start 3"): starts that many free slots, lowest first - `headless` (boolean): false = windowed (visible), true = headless (hidden). true only if the user says "headless/hidden/no window", false for "visible/headful". If unstated, omit and ask first (no guessing). Applies only… - `proxies` (array): Per-slot proxies, paired in slots order (count: launch order) - `proxy` (string): Only when the user asks for a proxy (never otherwise). As given: "1.2.3.4:8080", "http://user:pass@host:port", "socks5://host:port", "host:port:user:pass", etc. Applies to all launched slots, first l… - `slot` (integer): One slot to start (1-30). Omit if the user gave no number → lowest free slot - `slots` (array): Slot numbers to start at once (e.g. [1,2,3]), lowest first - `url` (string): Same start URL for every launched slot (e.g. "https://mail.google.com"). For per-slot or partial URLs use urls instead. Pass it when the start page is known so subagents need no separate navigation - `urls` (array): Per-slot start URLs, paired in slots order (count: launch order). "" = blank tab. E.g. slots [1,2], urls ["https://www.wehago.com", "https://test.igel.kr"] → 1 opens wehago, 2 opens test.igel.kr ### `browser_close` (~114 tokens) Close slot Closes slot Chrome cleanly (session and cookies saved). The profile (logins) is kept. Reports if another agent used it recently. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. ### `browser_tabs` (~131 tokens) List tabs Slot tab list: number, ID, title, URL, opener, last action, per-tab summary (updated only by actions with summary). "·front" marks the tab currently in front in its window (one per window). Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. ### `browser_tab_new` (~176 tokens) New tab Opens a new tab in the slot and returns its ID. When agents share a slot, open your own tab and work only by its ID to avoid mixing. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `url` (string): URL to open (omit for blank tab) ### `browser_tab_close` (~114 tokens) Close tab Closes a tab. tab is required. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number, required): Tab to close: number or ID ("t7") ### `browser_tab_select` (~150 tokens) Bring tab to front Brings a tab to the front of its Chrome window. Changes what the user sees, so use only when the user wants it. (Background tabs can be read, operated and captured; no need to bring them forward to work.) Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number, required): Tab to bring forward: number or ID ### `browser_snapshot` (~360 tokens) Snapshot Reads the tab as accessibility-tree text. Clickable/typable elements get refs like [e12]. Long pages are split; only page 1 (top) is shown (page=2 to continue; refs stay the same across pages). find="text" shows only matching elements with their parent context; ref="e40" shows only that element's subtree. Refs change when the page changes, so re-snapshot before acting. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `find` (string): Only lines containing this text, with parent context (ignores case and spaces). If unsure of site language, use | for alternatives, e.g. "제목|subject" - `interactive` (boolean): Only actionable elements (lines with refs): inputs, buttons, links. Use first to find inputs on big pages like Gmail - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `page` (integer): Page number for long output (default 1) - `ref` (string): Only this ref element and its subtree - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_text` (~234 tokens) Read text Reads the page body text (main/article if present). With ref, only that element's text. Shorter and easier than a snapshot for articles/documents. Use page for long text. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `page` (integer): Page number for long output (default 1) - `ref` (string): Only this element's text - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_screenshot` (~210 tokens) Screenshot Captures the visible area of the tab as PNG, even background tabs (without switching). Never changes window size or viewport, so full-page capture is unsupported (scroll then capture, or use snapshot/text). Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_navigate` (~293 tokens) Navigate Navigates the tab to a URL and waits for the body to load. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. - `url` (string, required): URL to go to ### `browser_back` (~269 tokens) Back Go back. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_forward` (~273 tokens) Forward Go forward (after going back). Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_reload` (~311 tokens) Reload Reloads the page (same as Chrome reload). ignore_cache=true bypasses the cache. Careful: unsaved user input on the page is lost. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `ignore_cache` (boolean): Bypass cache (hard reload) - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_dialog` (~407 tokens) Handle dialog Accepts (accept: true) or dismisses (accept: false) an open dialog (alert/confirm/prompt/beforeunload). The tab is frozen while a dialog is open. Usually judge from its content and handle it yourself (accept if it is part of the requested task; close unneeded notices/ads). Ask the user only when it confirms an irreversible action they didn't request (payment, deletion, etc.). beforeunload: accept = leave page (input lost), dismiss = stay. For prompt, text is the input. Input parameters: - `accept` (boolean, required): true = OK, false = cancel - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. - `text` (string): Text for a prompt dialog (used only when accepting) ### `browser_permission` (~292 tokens) Answer permission bubble Lists or answers Chrome permission bubbles ("site wants to: access other apps and services on this device / show notifications / know your location…"). They are browser UI: not in snapshot/screenshot, page tools can't click them, and the page often waits until they are answered. The header warns when one is open. Without button: shows the open bubbles with their exact button names. With button: presses that button (exact name as listed, e.g. "허용", "Allow", "Block", "Allow while visiting the site"). Windows, windowed slots only. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `button` (string): Exact button name to press, as listed in the header or by calling without button - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `site` (string): Only when several bubbles are open: part of the bubble title (e.g. the site host) to pick one - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. ### `browser_hover` (~308 tokens) Hover Moves the real mouse over a ref element (no click). For hover menus and tooltips. Use read=changes to see the opened menu. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `ref` (string, required): ref of the element to hover - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_drag` (~414 tokens) Drag Drags with the real mouse (press → move in steps → release): drag and drop, sliders, reordering, drag CAPTCHAs, etc. Target: to (element ref), to_text (text at the drop spot), or dx/dy (pixels from from). HTML drag is handled without starting an OS drag. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `dx` (number): Horizontal pixels (right +) - `dy` (number): Vertical pixels (down +) - `from` (string, required): ref of the element to drag (including ones marked draggable) - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. - `to` (string): ref of the drop target - `to_text` (string): Text shown at the drop spot (when it has no ref, e.g. "Drop here") ### `browser_download_wait` (~138 tokens) Wait for download Waits for the most recently started download to finish and returns the saved file path (user's Chrome download folder). Call after clicking the download button. Returns as soon as it finishes. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `timeout` (number): Max wait in seconds (default 120) ### `browser_pdf` (~229 tokens) Save as PDF Saves the page as a PDF (receipts, articles, etc.). Without path, saves to the user's Downloads folder named after the page title. Doesn't change the screen or window. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `path` (string): File path to save (e.g. C:\Users\me\Desktop\receipt.pdf) - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_click` (~375 tokens) Click Clicks a ref element with real mouse events. If another element covers it, doesn't click and reports it. Waits for loading if the click navigates; reports new tabs. Clicking a file input or "attach" button intercepts the OS file picker (not shown); then use browser_upload. Doesn't click or its label), or for a site's custom "attach" button, click it first with browser_click (CDPM intercepts the picker) and call without ref. The site gets the same events as a human file pick. Input parameters: - `agent` (string): Your display name, shown to other agents. Subagents must always set it. Default "claude-84f3". - `files` (array, required): File paths on this PC (absolute recommended) - `multiSlot` (boolean): true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest) - `read` (string): Append the page after the action (no separate read needed): text=body text, snapshot=snapshot page 1 (with refs), changes=only lines added/removed since your last snapshot (shortest; full page if the… - `ref` (string): File input ref. Omit to use the file picker just opened by a click - `slot` (integer, required): Browser slot 1-30. "3", "slot 3", "browser 3" → 3. If the user gives a port like 14052, subtract 14049. - `summary` (string): One-line note of what you are doing (e.g. "comparing laptop prices"). Shown in browser_status (not the status line). Omit to keep the previous one. - `tab` (string|number): Target tab: number (1, 2…) or ID ("t7"). Use the stable ID when agents share a slot. Required for action tools when there are multiple tabs. ### `browser_select` (~355 tokens) Select option Picks an option in a