Name: Cdpm
Author: IGELHARINE

Cdpm MCP

Lets many Claude Code sessions and subagents share numbered, logged-in Chrome instances over CDP

Grade A Local · stdio No auth needed 36 tools v0.1.9 MIT

No reviews yet by IGELHARINEnpm 1,841 Runs on your machine, nothing hosted

93/100

trust score

downloads a day

local

runs on your machine

downloads in 30d

What it does

Lets many Claude Code sessions and subagents share numbered, logged-in Chrome instances over CDP

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user cdpm-mcp '--' npx -y cdpm-mcp

# 2 — ask your agent for something these tools do
#   browser_status, browser_launch, browser_close and 33 more

Cdpm costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

IGELHARINE1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Shows running Chrome slots (1-30) with their tabs, opener, last action and one-line summary. Pass slot for just that slot.

Parameter	Type	Required	Notes
slot	integer	no	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".

Starts slot Chrome. Call only when the user explicitly asks (other tools never start a closed slot).

Parameter	Type	Required	Notes
slot	integer	no	One slot to start (1-30). Omit if the user gave no number → lowest free slot
slots	array	no	Slot numbers to start at once (e.g. [1,2,3]), lowest first
count	integer	no	When the user gives only a count ("start 3"): starts that many free slots, lowest first
url	string	no	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	no	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
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
headless	boolean	no	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 o
proxy	string	no	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 la
proxies	array	no	Per-slot proxies, paired in slots order (count: launch order)

Closes slot Chrome cleanly (session and cookies saved). The profile (logins) is kept. Reports if another agent used it recently.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".

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).

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".

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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
url	string	no	URL to open (omit for blank tab)
summary	string	no	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.

Closes a tab. tab is required.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		yes	Tab to close: number or ID ("t7")

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.)

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		yes	Tab to bring forward: number or ID

Reads the tab as accessibility-tree text. Clickable/typable elements get refs like [e12].

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	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	no	Page number for long output (default 1)
find	string	no	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	no	Only actionable elements (lines with refs): inputs, buttons, links. Use first to find inputs on big pages like Gmail
ref	string	no	Only this ref element and its subtree

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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	no	Only this element's text
page	integer	no	Page number for long output (default 1)

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).

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)

Navigates the tab to a URL and waits for the body to load.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
url	string	yes	URL to go to
read	string	no	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
summary	string	no	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.

Go back.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	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	no	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
summary	string	no	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.

Go forward (after going back).

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	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	no	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
summary	string	no	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.

Reloads the page (same as Chrome reload). ignore_cache=true bypasses the cache. Careful: unsaved user input on the page is lost.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ignore_cache	boolean	no	Bypass cache (hard reload)
read	string	no	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
summary	string	no	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.

Accepts (accept: true) or dismisses (accept: false) an open dialog (alert/confirm/prompt/beforeunload). The tab is frozen while a dialog is open.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
accept	boolean	yes	true = OK, false = cancel
text	string	no	Text for a prompt dialog (used only when accepting)
read	string	no	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
summary	string	no	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.

Lists or answers Chrome permission bubbles ("site wants to: access other apps and services on this device / show notifications / know your location…").

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
button	string	no	Exact button name to press, as listed in the header or by calling without button
site	string	no	Only when several bubbles are open: part of the bubble title (e.g. the site host) to pick one

Moves the real mouse over a ref element (no click). For hover menus and tooltips. Use read=changes to see the opened menu.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	yes	ref of the element to hover
read	string	no	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
summary	string	no	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.

Drags with the real mouse (press → move in steps → release): drag and drop, sliders, reordering, drag CAPTCHAs, etc.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
from	string	yes	ref of the element to drag (including ones marked draggable)
to	string	no	ref of the drop target
to_text	string	no	Text shown at the drop spot (when it has no ref, e.g. "Drop here")
dx	number	no	Horizontal pixels (right +)
dy	number	no	Vertical pixels (down +)
read	string	no	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
summary	string	no	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.

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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
timeout	number	no	Max wait in seconds (default 120)

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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	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	no	File path to save (e.g. C:\Users\me\Desktop\receipt.pdf)

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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	yes	ref from browser_snapshot (e.g. "e12")
double	boolean	no	Double-click
read	string	no	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
summary	string	no	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.

Types text into a ref element, sending real key events (keydown/keypress/input/keyup) per character like a human.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	yes	ref of the element to type into
text	string	yes	Text to type
clear	boolean	no	Clear existing content
submit	boolean	no	Press Enter after
fast	boolean	no	Very long text: insert at once without key events
read	string	no	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
summary	string	no	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.

Fills several inputs on the same page in order (each cleared, typed with real key events, value verified).

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
fields	array	yes	Fields to fill (top to bottom)
submit	string	no	After filling: "Enter" or a button ref to click
read	string	no	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
summary	string	no	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.

Puts files into a file input (no OS file picker shown to the user). Give ref of the file input (<input type=file> or its label), or

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
files	array	yes	File paths on this PC (absolute recommended)
ref	string	no	File input ref. Omit to use the file picker just opened by a click
read	string	no	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
summary	string	no	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.

Picks an option in a <select> dropdown (by value or visible text; partial match OK). Focuses the dropdown and moves with keys (arrow keys on Windows/Linux, typing the first letters on macOS), so the page gets real events and no list popup opens. If nothing matches, lists the available options.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	yes	ref of the dropdown (combobox)
option	string	yes	Option value or text
read	string	no	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
summary	string	no	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.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
key	string	yes	—
read	string	no	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
summary	string	no	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.

Scrolls a ref element into view, or by dy pixels (positive = down, negative = up, default 600). Reports the actual resulting position.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
ref	string	no	—
dy	number	no	—
read	string	no	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
summary	string	no	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.

Waits until text appears; gone: that text disappears; url: the URL changes; enabled: that button/input becomes enabled;

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
text	string	no	Text to wait for
url	string	no	Until the URL contains this (e.g. "mail.google.com/mail"). "" = until it differs from the current URL
gone	string	no	Until this text disappears from the page (e.g. login form's "Password" gone = logged in)
seconds	number	no	Plain wait in seconds. Avoid: wait on a condition (text/gone/url) or slot_inbox wait instead
timeout	number	no	Max wait in seconds for text/gone/url/enabled/response/network_idle. 300-600 when waiting for a human login, etc.
network_idle	boolean	no	Until no network requests for 0.5s (before capture/read)
enabled	string	no	Until this ref element (button/input) becomes enabled
response	string	no	Until a network response whose URL contains this completes (e.g. "/api/search"). * ? wildcards work (matched against the full URL, e.g. "api.example.com/v1/items"). Returns the response body

Evaluates a JavaScript expression in the tab and returns the result as JSON. Escape hatch only when other tools can't do it.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
expression	string	yes	JS expression (Promises are awaited)
summary	string	no	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 network request list (newest at bottom). Records the latest 500 since CDPM first attached to the tab. Filter with filter (URL part), type (Document, XHR, Fetch, Script, Image, etc.), failed (failures only). For details pass the n-number to browser_network_detail.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
filter	string	no	Only requests whose URL contains this
type	string	no	Request type (e.g. XHR, Fetch, Document, Script, Image)
failed	boolean	no	Failed requests only
limit	integer	no	Max count (default 40, newest first)

Shows one request's headers, sent data and response body (start of it, if text). id is the n-number from browser_network.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
id	string	yes	Request number (e.g. "n12")
body	boolean	no	Include response body (default true)

Blocks tab network requests matching URL patterns (they fail). add adds, remove removes, clear removes all rules you set.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
tab		no	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.
multiSlot	boolean	no	true only when one agent must handle several slots together (e.g. comparing). Normally omit (one agent = one slot; use subagents for the rest)
add	array	no	URL patterns to block
remove	array	no	Patterns to unblock
clear	boolean	no	Remove all rules set by this session
summary	string	no	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.

Use only when the user says to pause (e.g. "pause 3"); agents never call it on their own. All action tools on the slot are refused and any browser_wait in progress stops at once.

Parameter	Type	Required	Notes
slot	integer	no	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
slots	array	no	Multiple slots (e.g. [1,2,3])
all	boolean	no	All running slots
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".

Use only when the user says to resume (e.g. "continue 3"); the agent owning a paused slot never calls it on its own. Unpauses and messages every agent on the slot to wake it (agents re-read the page and continue). all=true resumes every paused slot.

Parameter	Type	Required	Notes
slot	integer	no	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
slots	array	no	Multiple slots (e.g. [1,2,3])
all	boolean	no	All paused slots
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".

Sends a message to other agents (real-time collaboration). slot = the slot the recipient owns (to reach another slot's agent, use that slot number). Omit to to send to everyone on that slot.

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
text	string	yes	—
to	string	no	Recipient agent name

Shows your unread messages. With wait (seconds), waits up to that long for a new message (for real-time conversation).

Parameter	Type	Required	Notes
slot	integer	yes	Browser slot …-…. "3", "slot 3", "browser 3" → 3. If the user gives a port like …, subtract ….
agent	string	no	Your display name, shown to other agents. Subagents must always set it. Default "claude-…".
wait	number	no	Max seconds to wait for a new message; returns as soon as one arrives (use this instead of repeatedly checking the page while waiting for another agent)

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Cdpm or to call it, at any volume.

ATrust score 93 / 100

Release 0.1.9 · scanned 18 Oct 2026

Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.

Threat score100

Client score93

Findings6 threat · 3 capability

Capabilityhigh

Coveragesource

Verificationrepo

Surface digest30d3c15dc2def5a04580ad83a7089021eb5c9575c3465d7485bd79b8ba41926f

Score vectorthreat 100 → client 93

Term	Level	What it prices	Points
capability-exposure	high	capability blast radius (high) — client exposure if the model is manipulated	−6
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.

What the scan could actually read

A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.

Tool surfaceread

Implementation sourceread

Package metadataread

Live transportnot available

Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Capability — what it could do if the model were manipulated

Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.

Tool	Capability tags	Why the tag was assigned
browser_status	no tags
browser_launch	no tags
browser_close	no tags
browser_tabs	no tags
browser_tab_new	no tags
browser_tab_close	no tags
browser_tab_select	no tags
browser_snapshot	no tags
browser_text	no tags
browser_screenshot	no tags
browser_navigate	no tags
browser_back	no tags
browser_forward	no tags
browser_reload	no tags
browser_dialog	no tags
browser_permission	no tags
browser_hover	no tags
browser_drag	no tags
browser_download_wait	untrusted-input	untrusted-input: keyword "download"
browser_pdf	no tags
browser_click	no tags
browser_type	no tags
browser_fill	no tags
browser_upload	no tags
browser_select	no tags
browser_press_key	no tags
browser_scroll	no tags
browser_wait	no tags
browser_eval	code-exec	code-exec: keyword "eval" in tool name
browser_network	no tags
browser_network_detail	no tags
browser_block	no tags
slot_pause	no tags
slot_resume	no tags
slot_send	no tags
slot_inbox	untrusted-input	untrusted-input: keyword "read_message"

Toxic-flow graph

The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.

flow-1

Untrusted input can drive an external action even though no sensitive source is exposed.

Supply chain and provenance

Integrityfirst-seen

Surface digest30d3c15dc2def5a0

Scanned2026-10-18

This is the first scan of this surface here, so there is nothing yet to compare it against.

Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.

Where are you running it?

Tool surface

Release history

Cdpm MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also