All servers / Browser Tools
Browser Tools
MCP server exposing live browser telemetry (console logs, network requests, screenshots, Lighthouse audits) from your real Chrome session
Tested by ConnectATDScore 90 out of 100. Tested 2026-11-17 on package version 2.0.4. Package: @agentdeskai/browser-tools-mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 20 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (52.4 seconds including download)
- Tools offered: 16
- Last published: 2026-10-27
- Weekly downloads (npm): 4,122
- License: MIT · Direct dependencies: 6
Tools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
listBrowserTabsno parametersEvery browser tab that currently has DevTools open, with the tabId you can pass to any other tool. Call this when a result reported otherTabs above 0, or when the user mentions a page other than the one you have been reading. The tab marked isCurrent is the one every other tool u
getConsoleLogs5 of 5 parameters describedConsole output from the current tab. Use keywords and limit to keep responses small — an unfiltered read can be large. Pass tabId for a different tab, or allTabs to read every tab; the result reports which tab it came from.
getConsoleErrors5 of 5 parameters describedOnly error-level console output and uncaught exceptions from the current tab. Start here when diagnosing a failure. Pass tabId for a different tab, or allTabs to read every tab.
getNetworkLogs6 of 6 parameters describedXHR and fetch requests from the current tab, including status and timing. Credential headers are redacted. Pass tabId for a different tab, or allTabs to read every tab.
getNetworkErrors5 of 5 parameters describedOnly requests that failed or returned a 4xx/5xx status. An empty result means there were no failures, which is a success, not an error.
getSelectedElement1 of 1 parameter describedThe DOM element the user has selected in the Chrome DevTools Elements panel, with its attributes and markup.
getPageInfono parametersWhich page the browser is currently on. Call this before reading telemetry so you know what the logs describe. If connectedTabs is above 1, call listBrowserTabs before assuming this is the page the user means.
getConnectionStatusno parametersWhether the Chrome extension is connected and how much telemetry has been captured. Call this first when something returns nothing.
takeScreenshot2 of 2 parameters describedCaptures the visible area of the current tab and returns the image directly, plus the path it was saved to and the url captured. Pass tabId to capture a different tab.
refreshBrowser1 of 1 parameter describedReloads the inspected tab. Useful for capturing a clean reproduction after calling wipeLogs.
getBrowserStorage3 of 3 parameters describedLists localStorage, sessionStorage and cookie entries for the current page. Values are withheld unless includeValues is set, because they routinely contain session tokens.
wipeLogs1 of 1 parameter describedDiscards captured console and network entries for every tab, or one tab if you name it. Use before reproducing a problem so the next read contains only relevant output.
runAccessibilityAudit2 of 2 parameters describedLighthouse accessibility audit of the current page: contrast, labels, semantics and screen-reader support. Takes up to a minute and launches a separate headless browser.
runPerformanceAudit2 of 2 parameters describedLighthouse performance audit of the current page, including Core Web Vitals. Takes up to a minute and launches a separate headless browser.
runSEOAudit2 of 2 parameters describedLighthouse SEO audit of the current page: metadata, indexability and crawlability. Takes up to a minute and launches a separate headless browser.
runBestPracticesAudit2 of 2 parameters describedLighthouse best-practices audit of the current page: security, deprecated APIs and modern-web hygiene. Takes up to a minute and launches a separate headless browser.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.