Name: Playwright Browser
Price: 29 USD
Author: mcpdevpro

Playwright Browser MCP Hosted by mcprush

Drive a real browser from your agent

Grade A Remote · Streamable HTTP Buyer key only 25 tools v0.1.0 · 6 Sep 2026

No reviews yet by mcpdevpro Hosted here, behind our gateway

100/100

trust score

tools declared

remote

via our gateway

—

p95 latency

What it does

Microsoft's official Playwright MCP server with headless Chromium, hosted: your agent opens pages, reads them as accessibility snapshots, clicks, types, fills forms and takes screenshots. Built from the image mcr.microsoft.com/playwright/mcp (v0.0.82) and run on mcprush hosting: there is no endpoint to keep alive and nothing to deploy yourself. The browser runs in an isolated cloud container, so it reaches public HTTPS sites only: not your localhost, your intranet, plain http:// pages or your own logged-in sessions, and every session starts logged out. Screenshots and snapshots come back in the answer; files it saves are gone when the server stops after 15 idle minutes. The image is pinned, so what answers today is what answered yesterday.

Quickstart

# 1 — buy it first ($29 a month): mcprush.com/checkout?server=playwright-browser-hosted-mcp
#     a key alone is not enough: the gateway refuses every call until it is bought
# 2 — sign in with a key of the account that bought it: npx mcprush@latest login
#     the key is at mcprush.com/dashboard#access
# 3 — install
npx mcprush@latest add mcpdevpro/playwright-browser-hosted-mcp

# 4 — ask your agent for something these tools do
#   browser_close, browser_resize, browser_console_messages and 22 more

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.

PublisherVerified · since 2026

mcpdevpro11 servers

6 categories · publishing since 2026

All 11 servers

Installation

Where are you running it?

Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on infrastructure we host behind our gateway, and what you install is the connection to it.

Claude Codedeclared by this listing

Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Claude Code reads MCPRUSH_KEY each time it connects, so the key stays out of its config: export your key from Access in your shell profile (macOS, Linux), or run setx MCPRUSH_KEY <your key> and open a new terminal (Windows). Or let npx mcprush@latest add mcpdevpro/playwright-browser-hosted-mcp write the entry with the key for you; --scope user makes it available in every project. The first connection after a quiet spell starts the server, which takes up to a minute: if your client says it failed to connect, reconnect after that (/mcp in Claude Code).

Buy it first — $29 a month. A key alone is not enough: until this account has bought it, the gateway refuses every call. Subscribe, then use a key of the account that bought it.

claude mcp add --transport http --scope user playwright-browser-hosted-mcp https://mcprush.com/gw/playwright-browser-hosted-mcp/mcp --header 'Authorization: Bearer ${MCPRUSH_KEY}'

Reconnect, or start a new session, and the tools appear in the model’s tool list.

This is a paid listing: the gateway answers only a key of an account whose subscription to it is active — how the login works. Until then add writes nothing: signed out, it names the price and the checkout link; signed in, it prints the checkout link, or why the subscription is held (ended, paused, an unpaid invoice) and the link that lifts it. The gateway refuses every call the same way, and most clients only show the server as failed.

What it writes

One config entry pointing at the gateway. The server itself runs on infrastructure we host, so nothing from this listing executes on your machine.

What you approve

25 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.

Tool surface

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

Only tools that write or reach the network

Close the page

No parameter schema on file.

Resize the browser window

Parameter	Type	Required	Notes
width	number	yes	Width of the browser window
height	number	yes	Height of the browser window

Returns all console messages

Parameter	Type	Required	Notes
level	string	yes	Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to "info".
all	boolean	no	Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false.
filename	string	no	File name to save the console messages to. Relative file names are resolved against the workspace root. If not provided, messages are returned as text.

Handle a dialog

Parameter	Type	Required	Notes
accept	boolean	yes	Whether to accept the dialog.
promptText	string	no	The text of the prompt in case of a prompt dialog.

Emulate CSS media features for the page, for example switch between the light and dark color scheme. Omitted parameters are left unchanged; null clears an override.

Parameter	Required	Notes
colorScheme	no	Emulates the prefers-color-scheme media feature
reducedMotion	no	Emulates the prefers-reduced-motion media feature
forcedColors	no	Emulates the forced-colors media feature
contrast	no	Emulates the prefers-contrast media feature
media	no	Changes the CSS media type of the page

Evaluate JavaScript expression on page or element

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	no	Exact target element reference from the page snapshot, or a unique element selector
function	string	yes	() => { /* code / } or (element) => { / code */ } when element is provided
filename	string	no	File name to save the result to. Relative file names are resolved against the workspace root. If not provided, result is returned as text.

Upload one or multiple files

Parameter	Type	Required	Notes
paths	array	no	The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.

Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of "paths" or "data" must be provided.

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	yes	Exact target element reference from the page snapshot, or a unique element selector
paths	array	no	Absolute paths to files to drop onto the element.
data	object	no	Data to drop, as a map of MIME type to string value (e.g. {"text/plain": "hello", "text/uri-list": "https://example.com"}).

Search the accessibility snapshot of the current page for text or a regular expression. Returns matching snapshot nodes with a few lines of surrounding context (like search snippets), each shown under its path from the root of the tree, which is cheaper than capturing the whole snapshot when you only need to locate an element and its ref.

Parameter	Type	Required	Notes
text	string	no	Plain text to search for in the page snapshot (case-insensitive substring match). Provide either text or regex, not both.
regex	string	no	Regular expression to search for in the page snapshot. Matching is case-sensitive by default; wrap the pattern in slashes to add flags, e.g. "/error/i" for case-insensitive. Provide either text or reg

Fill multiple form fields

Parameter	Type	Required	Notes
fields	array	yes	Fields to fill in

Press a key on the keyboard

Parameter	Type	Required	Notes
key	string	yes	Name of the key to press or a character to generate, such as ArrowLeft or a

Type text into editable element

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	yes	Exact target element reference from the page snapshot, or a unique element selector
text	string	yes	Text to type into the element
submit	boolean	no	Whether to submit entered text (press Enter after)
slowly	boolean	no	Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.

Navigate to a URL

Parameter	Type	Required	Notes
url	string	yes	The URL to navigate to

Go back to the previous page in the history

No parameter schema on file.

Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details.

Parameter	Type	Required	Notes
static	boolean	yes	Whether to include successful static resources like images, fonts, scripts, etc. Defaults to false.
filter	string	no	Only return requests whose URL matches this regexp (e.g. "/api/.*user").
filename	string	no	File name to save the network requests to. Relative file names are resolved against the workspace root. If not provided, requests are returned as text.

Returns full details (headers and body) of a single network request, or a single part if part is set. Use the number from browser_network_requests.

Parameter	Type	Required	Notes
index	integer	yes	1-based index of the request, as printed by browser_network_requests.
part	string	no	Return only this part of the request. Omit to return full details.
filename	string	no	File name to save the result to. Relative file names are resolved against the workspace root. If not provided, output is returned as text.

Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent.

Parameter	Type	Required	Notes
code	string	no	A JavaScript function containing Playwright code to execute. It will be invoked with a single argument, page, which you can use for any page interaction. For example: `async (page) => { await page.get
filename	string	no	Load code from the specified file. Relative file names are resolved against the workspace root. If both code and filename are provided, code will be ignored.

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	no	Exact target element reference from the page snapshot, or a unique element selector
type	string	no	Image format for the screenshot. If unset, inferred from the filename extension, otherwise png.
filename	string	no	File name to save the screenshot to. Relative file names are resolved against the workspace root. If not specified, the screenshot is saved into the output directory as `page-{timestamp}.{png\|jpeg\|web
fullPage	boolean	no	When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots.
scale	string	yes	Image resolution scale. "css" produces a screenshot sized in CSS pixels (smaller, consistent across devices). "device" produces a high-resolution screenshot using device pixels (larger, accounts for t

Capture accessibility snapshot of the current page, this is better than screenshot

Parameter	Type	Required	Notes
target	string	no	Exact target element reference from the page snapshot, or a unique element selector
filename	string	no	Save snapshot to a file instead of returning it in the response. Relative file names are resolved against the workspace root.
depth	number	no	Limit the depth of the snapshot tree
boxes	boolean	no	Include each element's bounding box as [box=x,y,width,height] in the snapshot. Coordinates are viewport-relative, in CSS pixels (Element.getBoundingClientRect)

Perform click on a web page

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	yes	Exact target element reference from the page snapshot, or a unique element selector
doubleClick	boolean	no	Whether to perform a double click instead of a single click
button	string	no	Button to click, defaults to left
modifiers	array	no	Modifier keys to press

Perform drag and drop between two elements

Parameter	Type	Required	Notes
startElement	string	no	Human-readable source element description used to obtain the permission to interact with the element
startTarget	string	yes	Exact target element reference from the page snapshot, or a unique element selector
endElement	string	no	Human-readable target element description used to obtain the permission to interact with the element
endTarget	string	yes	Exact target element reference from the page snapshot, or a unique element selector

Hover over element on page

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	yes	Exact target element reference from the page snapshot, or a unique element selector

Select an option in a dropdown

Parameter	Type	Required	Notes
element	string	no	Human-readable element description used to obtain permission to interact with the element
target	string	yes	Exact target element reference from the page snapshot, or a unique element selector
values	array	yes	Array of values to select in the dropdown. This can be a single value or multiple values.

List, create, close, or select a browser tab.

Parameter	Type	Required	Notes
action	string	yes	Operation to perform
index	number	no	Tab index, used for close/select. If omitted for close, current tab is closed.
url	string	no	URL to navigate to in the new tab, used for new.

Wait for text to appear or disappear or a specified time to pass

Parameter	Type	Required	Notes
time	number	no	The time to wait in seconds
text	string	no	The text to wait for
textGone	string	no	The text to wait for to disappear

Starter

$29 / month

50,000 calls a month, included
120 calls a minute at peak
Every tool the listing has
Cancel any time — the unused days are credited
Runs behind the gateway, so cancelling stops it

What counts against the 50,000 calls a month on Starter

Tool	Unit	Calls used	Out of the monthly allowance
browser_close	write	2	0.0040%
browser_resize	write	2	0.0040%
browser_console_messages	call	1	0.0020%
browser_handle_dialog	write	2	0.0040%
browser_emulate_media	write	2	0.0040%
browser_evaluate	write	2	0.0040%
browser_file_upload	write	2	0.0040%
browser_drop	write	2	0.0040%

Failed calls, timeouts and anything the gateway rejects never count. When the allowance runs out the gateway returns an error naming the plan limit — nothing is billed beyond the subscription, ever.

ATrust score 100 / 100

Release 0.1.0 · scanned 6 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 score100

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationvendor

Surface digest243d70800d2e9b3d2d5b76c349af14574f6274dbed288ee70dc98d76b770668d

Score vectorthreat 100 → client 100

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	vendor	publisher verification (official vendor) — published under a known vendor’s authority	−0
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 surfacenot available

Implementation sourceread

Package metadataread

Live transportnot available

No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
No per-tool rows for this release — see the note below.

No tool surface was enumerated, so there is nothing to attribute a capability to.

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.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digest243d70800d2e9b3d

Scanned2026-10-06

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.