Control a real Chrome browser to complete any task: fill forms, extract data, book flights.
Nothing to run from here
Browserdebug 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.
96/100
trust score
12
downloads a day
local
runs on your machine
244
downloads in 30d
What it does
Debug web pages in Chrome: performance traces, network, console, snapshots, screenshots.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user browserdebug-mcp '--' npx -y @reneturcios/browserdebug mcp
# 2 — ask your agent for something these tools do
# click, drag, fill and 23 more
Browserdebug 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 326 servers
CloudCorpRecords326 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 Browserdebug 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 browserdebug-mcp '--' npx -y @reneturcios/browserdebug 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
26 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.
Click on the provided element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dblClick | boolean | no | Whether to double click the element |
| uid | string | yes | The uid of the element from a page snapshot to click |
Drag an element onto another element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from_uid | string | yes | The uid of the element to drag from |
| to_uid | string | yes | The uid of the element to drag onto |
Type text into an input, text area or select an option from a select element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| uid | string | yes | The uid of the input, text area, or select element to fill |
| value | string | yes | The text to type into the element, or the value of the option to select |
Fill out multiple form elements at once
| Parameter | Type | Required | Notes |
|---|---|---|---|
| elements | array | yes | The form elements to fill, each given as an element uid and the value to enter |
Handle a browser dialog (accept or dismiss)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | The dialog action to take: accept or dismiss |
| promptText | string | no | Optional text to enter into a prompt dialog before accepting it |
Hover over the provided element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| uid | string | yes | The uid of the element from a page snapshot to hover over |
Press a key or key combination in the browser
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | The key or key combination to press, such as Enter or Control+A |
Upload a file through a file input element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | yes | The local path of the file to upload |
| uid | string | yes | The uid of the file input element to upload through |
Closes the page by its index; the last open page cannot be closed
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pageId | number | yes | The index of the page to close, as listed by list_pages |
Get a list of pages open in the browser
No parameter schema on file.
Navigate the currently selected page to a URL, or back, forward or reload
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ignoreCache | boolean | no | Whether to ignore the browser cache when reloading the page |
| timeout | number | no | Optional navigation timeout in milliseconds |
| type | string | no | Optional navigation type: url, back, forward, or reload |
| url | string | no | The URL to navigate to when the navigation type is url |
Open a new tab and load a URL
| Parameter | Type | Required | Notes |
|---|---|---|---|
| background | boolean | no | Whether to open the new tab in the background without selecting it |
| timeout | number | no | Optional navigation timeout in milliseconds |
| url | string | yes | The URL to load in the new tab |
Select a page as the context for future tool calls
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bringToFront | boolean | no | Whether to bring the selected page to the front |
| pageId | number | yes | The index of the page to select, as listed by list_pages |
Wait until any of the provided texts appears on the selected page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | array | yes | The texts to wait for; the call returns when any one of them appears on the page |
| timeout | number | no | Optional timeout in milliseconds to wait for the text |
Emulates network, CPU, geolocation, user agent and colour scheme features on the selected page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| colorScheme | string | no | Optional colour scheme to emulate: light, dark, or auto |
| cpuThrottlingRate | number | no | Optional CPU throttling rate; 1 means no throttling and the value must be at least 1 |
| geolocation | string | no | Optional geolocation to emulate, given as a latitude and longitude pair |
| networkConditions | string | no | Optional network conditions preset to emulate, such as Slow 3G or Fast 3G |
| userAgent | string | no | Optional user agent string to emulate |
Resizes the selected page's window so the page fits the given dimensions
| Parameter | Type | Required | Notes |
|---|---|---|---|
| height | number | yes | The new window height in pixels |
| width | number | yes | The new window width in pixels |
Provide more detailed information on a specific performance insight from a recorded trace
| Parameter | Type | Required | Notes |
|---|---|---|---|
| insightName | string | yes | The name of the performance insight to analyse |
| insightSetId | string | yes | The id of the insight set from a recorded performance trace |
Start a performance trace on the selected page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| autoStop | boolean | no | Whether to stop the trace automatically once the page has loaded |
| filePath | string | no | Optional file path to save the trace to when it stops |
| reload | boolean | no | Whether to reload the page after starting the trace |
Stop the active performance trace
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | no | Optional file path to save the stopped trace to |
Get a network request by its request id; without an id, the currently selected request in DevTools
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reqid | number | no | Optional request id of the network request; the request currently selected in DevTools is used when omitted |
List all requests for the currently selected page since navigation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| includePreservedRequests | boolean | no | Whether to include requests preserved from the previous navigation |
| pageIdx | number | no | Optional page index of the request list to return |
| pageSize | number | no | Optional maximum number of requests to return in one page of results |
| resourceTypes | array | no | Optional list of resource types to filter the requests by |
Evaluate a JavaScript function inside the currently selected page and return its result
| Parameter | Type | Required | Notes |
|---|---|---|---|
| args | array | no | Optional element uids to pass to the function as its arguments |
| function | string | yes | The JavaScript function declaration to evaluate inside the selected page |
Get a console message by its id
| Parameter | Type | Required | Notes |
|---|---|---|---|
| msgid | number | yes | The id of the console message, as listed by list_console_messages |
List all console messages for the currently selected page since navigation
| Parameter | Type | Required | Notes |
|---|---|---|---|
| includePreservedMessages | boolean | no | Whether to include messages preserved from the previous navigation |
| pageIdx | number | no | Optional page index of the message list to return |
| pageSize | number | no | Optional maximum number of messages to return in one page of results |
| types | array | no | Optional list of console message types to filter by, such as log, error, or warning |
Take a screenshot of the page or an element
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | no | Optional file path to save the screenshot to |
| format | string | no | Optional image format of the screenshot: png, jpeg, or webp |
| fullPage | boolean | no | Whether to capture the full page instead of the visible viewport |
| quality | number | no | Optional image quality from 0 to 100, for the jpeg and webp formats |
| uid | string | no | Optional uid of an element to screenshot instead of the page |
Take a text snapshot of the currently selected page based on the accessibility tree
| Parameter | Type | Required | Notes |
|---|---|---|---|
| filePath | string | no | Optional file path to save the snapshot to |
| verbose | boolean | no | Whether to include verbose accessibility tree details in the snapshot |
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 Browserdebug 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 96 / 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 score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest39c50388cf4b10a2ea9a9eb6127b541c437f142dcc89ce6649c19d6ddf163c2a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (26 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| click | no tags | |
| drag | no tags | |
| fill | no tags | |
| fill_form | no tags | |
| handle_dialog | no tags | |
| hover | no tags | |
| press_key | no tags | |
| upload_file | external-sink | external-sink: keyword "upload_file" |
| close_page | no tags | |
| list_pages | no tags | |
| navigate_page | no tags | |
| new_page | no tags | |
| select_page | no tags | |
| wait_for | no tags | |
| emulate | no tags | |
| resize_page | no tags | |
| performance_analyze_insight | no tags | |
| performance_start_trace | no tags | |
| performance_stop_trace | no tags | |
| get_network_request | no tags | |
| list_network_requests | no tags | |
| evaluate_script | no tags | |
| get_console_message | no tags | |
| list_console_messages | no tags | |
| take_screenshot | no tags | |
| take_snapshot | 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 digest39c50388cf4b10a2
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 Browserdebug 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.