Browserdebug

io.github.CloudCorpRecordsPublished by GitHub account CloudCorpRecordsv0.1.0Updated Nov 7, 2026

Debug web pages in Chrome: performance traces, network, console, snapshots, screenshots.

VerifiedSTDIODesktop onlyBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Chrome DevTools-style debugging for an assistant: drive pages, record performance traces, and inspect network, console, snapshots and screenshots.

What you can do
  • Navigate, open, select and close pages, and wait for text to appear
  • Click, hover, drag, type into fields, fill forms, press keys, handle dialogs and upload files
  • Take accessibility-tree snapshots and screenshots of pages or elements
  • Start and stop performance traces and read detailed insight on a recorded trace
  • List and inspect network requests and console messages for the selected page
  • Emulate network, CPU, geolocation, user agent and colour scheme, resize the window, and evaluate JavaScript in the page
When to use it
Useful when an assistant needs to reproduce or diagnose a web page problem: checking console errors, tracing slow loads, inspecting requests, or scripting form and click flows against a real Chrome session.
Requirements
Runs locally over stdio via npx or the Docker image. The package bundles no browser and downloads none; browser commands fail with a "Browser unavailable" error unless a DevTools-protocol-compatible executor is injected. No authentication, environment variables or headers are declared.
Before you install
Tools act on a live browser: they click, type, submit forms, upload files, evaluate JavaScript and change emulation settings, which can change data or trigger actions on visited sites. Uploading files sends local file contents to the page. Traces and network inspection expose page data to the assistant.

Installation

In SourceWeft

  1. Open Browserdebug in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

browserdebug

Chrome DevTools-style debugging as a CLI and a stdio MCP server in one bin. Record performance traces and read their insights, list and inspect network requests, read console messages, take text snapshots and screenshots, emulate network/CPU/device conditions, and drive page input by element uid.

The browser sits behind an injectable executor interface (DebugBrowser in src/types.ts). This package bundles no browser and downloads none: with no executor configured, browser commands fail with a clear "Browser unavailable" error. Deployments inject a DevTools-protocol-compatible executor to drive a real Chrome. The performance-trace state machine lives in the core: a trace must be started before it can be stopped, and cannot be started twice.

Install

bash
npx -y @reneturcios/browserdebug mcp

CLI

bash
browserdebug mcpbrowserdebug pagesbrowserdebug navigate <url>browserdebug snapshotbrowserdebug screenshot [file]browserdebug --version

Exit codes: 0 success, 1 browser error, 2 usage error.

MCP tools

26 tools: click, drag, fill, fill_form, handle_dialog, hover, press_key, upload_file, close_page, list_pages, navigate_page, new_page, select_page, wait_for, emulate, resize_page, performance_analyze_insight, performance_start_trace, performance_stop_trace, get_network_request, list_network_requests, evaluate_script, get_console_message, list_console_messages, take_screenshot, take_snapshot.

MCP client config:

json
{  "mcpServers": {    "browserdebug": {      "command": "npx",      "args": ["-y", "@reneturcios/browserdebug", "mcp"]    }  }}

Docker

bash
docker run -i ghcr.io/cloudcorprecords/browserdebug          # MCP serverdocker run --rm ghcr.io/cloudcorprecords/browserdebug --version

Development

bash
npm installnpm run buildnpm test

MIT license.

Source: README.md at commit 6fe938b

Tools

26

click

Click on the provided element

ParametersuidrequireddblClick

drag

Drag an element onto another element

Parametersto_uidrequiredfrom_uidrequired

fill

Type text into an input, text area or select an option from a select element

Parametersuidrequiredvaluerequired

fill_form

Fill out multiple form elements at once

Parameterselementsrequired

handle_dialog

Handle a browser dialog (accept or dismiss)

ParametersactionrequiredpromptText

hover

Hover over the provided element

Parametersuidrequired

press_key

Press a key or key combination in the browser

Parameterskeyrequired

upload_file

Upload a file through a file input element

ParametersuidrequiredfilePathrequired

close_page

Closes the page by its index; the last open page cannot be closed

ParameterspageIdrequired

list_pages

Get a list of pages open in the browser

Takes no parameters.

navigate_page

Navigate the currently selected page to a URL, or back, forward or reload

ParametersurltypetimeoutignoreCache

new_page

Open a new tab and load a URL

Parametersurlrequiredtimeoutbackground

select_page

Select a page as the context for future tool calls

ParameterspageIdrequiredbringToFront

wait_for

Wait until any of the provided texts appears on the selected page

Parameterstextrequiredtimeout

emulate

Emulates network, CPU, geolocation, user agent and colour scheme features on the selected page

ParametersuserAgentcolorSchemegeolocationcpuThrottlingRatenetworkConditions

resize_page

Resizes the selected page's window so the page fits the given dimensions

Parameterswidthrequiredheightrequired

performance_analyze_insight

Provide more detailed information on a specific performance insight from a recorded trace

ParametersinsightNamerequiredinsightSetIdrequired

performance_start_trace

Start a performance trace on the selected page

ParametersreloadautoStopfilePath

performance_stop_trace

Stop the active performance trace

ParametersfilePath

get_network_request

Get a network request by its request id; without an id, the currently selected request in DevTools

Parametersreqid

list_network_requests

List all requests for the currently selected page since navigation

ParameterspageIdxpageSizeresourceTypesincludePreservedRequests

evaluate_script

Evaluate a JavaScript function inside the currently selected page and return its result

Parametersargsfunctionrequired

get_console_message

Get a console message by its id

Parametersmsgidrequired

list_console_messages

List all console messages for the currently selected page since navigation

ParameterstypespageIdxpageSizeincludePreservedMessages

take_screenshot

Take a screenshot of the page or an element

ParametersuidformatqualityfilePathfullPage

take_snapshot

Take a text snapshot of the currently selected page based on the accessibility tree

ParametersverbosefilePath

Version history

1
  1. v0.1.0LatestOct 31, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts
  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts