$ loading_
Control Chrome for debugging, automation, and performance analysis via DevTools.
This MCP tool appears to control a live local Chrome browser via Chrome DevTools, which implies local process interaction and browser-level data access, so it falls under caution. It does not declare required secrets or fixed remote endpoints, and it is open source and auditable, but adoption is low and maintenance is unknown, so it should be used in a constrained environment.
The materials explicitly state that no keys or environment variables are required, and there is no stated need for API tokens, account passwords, or other sensitive secrets; credential exposure appears low.
No fixed remote endpoint is declared, so the tool itself does not explicitly expose a direct data-exfiltration destination; however, it controls a live Chrome instance, and the browser may reach sites the user has open, meaning page content and interaction data could leave via the browser's network stack depending on actual usage.
The system flags executes-code, and the description indicates it controls Chrome via DevTools for automation, debugging, and analysis, which typically means launching or attaching to a local browser process and invoking DevTools capabilities. This kind of local execution/process control is normal for an MCP tool and warrants caution, but no specific red flag of excessive execution is stated in the materials.
By inspecting and controlling a live Chrome instance through DevTools, the tool can typically access the current page DOM, console, network activity, performance data, and other loaded browser-session content; this implies indirect access to user browsing data. The materials do not state that it requests extra system-level file access or unrelated resources, and no clear evidence of overbroad authorization is present.
The project is open source under Apache 2.0 and therefore auditable, which is a meaningful risk-reducing factor; however, it comes from a third-party registry, the GitHub repository has 0 stars, maintenance status is unknown, and there is a slight naming mismatch between the tool and repo (chrome-devtools-mcp vs chrpme_MCP), which adds uncertainty around provenance and ongoing maintenance.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "chrome-devtools-mcp" yet — see the docs or source repo.
Open the target webpage, reproduce the error flow, inspect the Console, Network, and Elements panels, identify the frontend issue causing the button click failure, and suggest a fix.
A report with the root cause, related requests or DOM issues, reproduction steps, and actionable fix recommendations.
Use browser automation to open the signup page, test required-field validation, error messages, and the successful submission flow, then record results and screenshots for each step.
A form testing report including pass/fail results, key screenshots, and a list of issues found.
Open the homepage and record performance data, analyze why first-screen loading is slow, focus on network requests, script execution, and rendering time, and propose optimization priorities.
A performance analysis summary highlighting major bottlenecks, key metrics, and prioritized optimization recommendations.
Control and inspect live Chrome for automation, debugging, and performance analysis.
Control Chrome DevTools with AI for debugging, screenshots, and script execution.
Connect Chrome DevTools to help AI agents debug and inspect web pages.
Connect Chrome DevTools so AI can debug pages and inspect performance.
Control a real Chrome browser for browsing, interaction, and page reading.
Automate Chrome with natural language for page analysis, workflow recording, and visual testing.