Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Browserstage is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
12
downloads a day
local
runs on your machine
238
downloads in 30d
What it does
Automate a browser with accessibility snapshots: navigate, click, type, fill and wait.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user browserstage-mcp '--' npx -y @reneturcios/browserstage mcp
# 2 — ask your agent for something these tools do
# browser_navigate, browser_navigate_back, browser_snapshot and 21 more
Browserstage costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 278 servers
CloudCorpRecords278 servers
28 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Browserstage as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user browserstage-mcp '--' npx -y @reneturcios/browserstage mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
24 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Navigate to a URL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | The URL to navigate the page to |
Go back to the previous page in the browser history
No parameter schema on file.
Capture accessibility snapshot of the current page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| depth | number | no | Optional maximum depth of the accessibility tree to capture |
| filename | string | no | Optional filename to save the snapshot to |
| target | string | no | Optional element reference from a page snapshot to scope the snapshot to |
Search the accessibility snapshot for text or a regular expression
| Parameter | Type | Required | Notes |
|---|---|---|---|
| regex | string | no | Optional regular expression to search for in the page snapshot |
| text | string | no | Optional text to search for in the page snapshot |
Perform click on a web page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| button | string | no | Optional mouse button to click with: left, right, or middle |
| doubleClick | boolean | no | Whether to double click the element |
| element | string | yes | Human-readable description of the element to click |
| target | string | yes | Element reference from a page snapshot to click |
Hover over an element on the page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | string | yes | Human-readable description of the element to hover over |
| target | string | yes | Element reference from a page snapshot to hover over |
Perform drag and drop between two elements
| Parameter | Type | Required | Notes |
|---|---|---|---|
| endElement | string | yes | Human-readable description of the element to drop onto |
| endTarget | string | yes | Element reference of the element to drop onto |
| startElement | string | yes | Human-readable description of the element to drag from |
| startTarget | string | yes | Element reference of the element to drag from |
Drop files or data onto an element on the page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | string | yes | Human-readable description of the element to drop onto |
| paths | array | no | Optional file paths to drop onto the element |
| target | string | yes | Element reference of the element to drop onto |
Select an option in a dropdown
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | yes | Element reference of the dropdown to select an option in |
| values | array | yes | The option values to select in the dropdown |
Type text into an editable element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | string | yes | Human-readable description of the editable element to type into |
| slowly | boolean | no | Whether to type the text one character at a time |
| submit | boolean | no | Whether to press Enter after typing |
| target | string | yes | Element reference of the element to type into |
| text | string | yes | The text to type into the element |
Press a key on the keyboard
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | The key to press, such as Enter, ArrowDown, or a single character |
Fill multiple form fields
| Parameter | Type | Required | Notes |
|---|---|---|---|
| fields | array | yes | The form fields to fill; each field carries a name, a type, a value, and an optional element target |
Take a screenshot of the current page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filename | string | no | Optional filename to save the screenshot to |
| fullPage | boolean | no | Whether to capture the full scrollable page instead of the viewport |
| target | string | no | Optional element reference from a page snapshot to screenshot instead of the page |
| type | string | no | Optional image format of the screenshot, such as png or jpeg |
Run a Playwright code snippet against the current page (unsafe: arbitrary code execution)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | yes | The Playwright code snippet to run against the current page |
Evaluate JavaScript expression on the page or on an element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| element | string | no | Optional human-readable description of the element to evaluate on |
| function | string | yes | The JavaScript function to evaluate on the page or on an element |
| target | string | no | Optional element reference to evaluate the function on |
Wait for text to appear or disappear, or for a specified time to pass
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | no | Optional text to wait for the page to contain |
| textGone | string | no | Optional text to wait for the page to no longer contain |
| time | number | no | Optional time in seconds to wait |
Handle a browser dialog
| Parameter | Type | Required | Notes |
|---|---|---|---|
| accept | boolean | yes | Whether to accept the dialog (true) or dismiss it (false) |
| promptText | string | no | Optional text to enter into a prompt dialog |
Upload one or multiple files
| Parameter | Type | Required | Notes |
|---|---|---|---|
| paths | array | no | Optional file paths to upload; when omitted, an open file chooser is cancelled |
Returns all console messages
| Parameter | Type | Required | Notes |
|---|---|---|---|
| all | boolean | no | Whether to return console messages for all frames, not just the current page |
| filename | string | no | Optional filename to save the console messages to |
| level | string | no | Optional console message level to return: info, warning, error, or debug |
Returns a numbered list of network requests since loading the page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filename | string | no | Optional filename to save the request list to |
| static | boolean | no | Optional flag to filter the list by static resource requests |
Returns the full details of a single network request
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filename | string | no | Optional filename to save the request details to |
| index | number | yes | The index of the network request in the browser_network_requests list |
List, create, close, or select a browser tab
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | The tab action to perform: list, new, close, or select |
| index | number | no | Optional index of the tab for the close and select actions |
| url | string | no | Optional URL to open when the action is new |
Close the current page and the browser
No parameter schema on file.
Resize the browser window
| Parameter | Type | Required | Notes |
|---|---|---|---|
| height | number | yes | The new browser window height in pixels |
| width | number | yes | The new browser window width in pixels |
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
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Browserstage or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.1.0 · scanned 31 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
Findings0 threat · 3 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest605b0ca30bedc2096241ea8b4e2c2fc1d87a74daf279858b1f38ce2118048d94
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 (24 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_navigate | no tags | |
| browser_navigate_back | no tags | |
| browser_snapshot | no tags | |
| browser_find | no tags | |
| browser_click | no tags | |
| browser_hover | no tags | |
| browser_drag | no tags | |
| browser_drop | no tags | |
| browser_select_option | no tags | |
| browser_type | no tags | |
| browser_press_key | no tags | |
| browser_fill_form | no tags | |
| browser_take_screenshot | no tags | |
| browser_run_code_unsafe | code-exec | code-exec: keyword "run_code" in tool name |
| browser_evaluate | no tags | |
| browser_wait_for | no tags | |
| browser_handle_dialog | no tags | |
| browser_file_upload | no tags | |
| browser_console_messages | no tags | |
| browser_network_requests | no tags | |
| browser_network_request | no tags | |
| browser_tabs | no tags | |
| browser_close | no tags | |
| browser_resize | no tags |
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 digest605b0ca30bedc209
Scanned2026-10-31
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.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.1.0. Pin a release below and the command asks for exactly that one.
0.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Browserstage can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.