$ loading_
Control Chrome and automate multi-session browsing through MCP clients.
The materials describe an open-source local Chrome automation MCP server with no extra secrets required and no declared standalone remote endpoint, with no clear high-risk red flags observed. The main concerns are its inherent local process/browser-control capabilities and the relatively low community adoption with unknown maintenance status.
The materials explicitly state that no keys or environment variables are required, and there is no indication that API keys, OAuth tokens, or other sensitive credentials are needed; credential exposure appears limited.
No fixed remote endpoint is declared, and there is no stated behavior of sending data to a proprietary third-party service; however, as a Chrome automation tool it will drive browser visits to web pages, so user inputs and page content may be transmitted to the sites being visited as part of normal browser activity.
The system checks already mark this tool as executes-code, and the description as a standalone MCP server for Chrome automation reasonably implies launching and controlling local browser-related processes. This is a normal local execution capability for this class of tool, with no evidence of extra privilege escalation or unusual system permission requests in the materials.
Its stated function is browser control and page interaction, which typically allows access to page contents, form inputs, and data visible within browser sessions, and may trigger browser actions such as downloads/uploads; the materials do not state direct access to local files beyond the browser context, and no obvious overbroad authorization is described.
There is a public GitHub repository under the MIT license, which improves auditability and lowers risk; however, the source is a third_party_registry entry, community adoption is only 0 stars, and maintenance status is unknown, so trust and ongoing-maintenance signals are relatively weak and the code/dependencies should be reviewed.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ChromeCP" yet — see the docs or source repo.
Use ChromeCP to open the target website, log in, extract the table data on the page, and return it in a structured format.
Returns post-login table data in a structured format.
Use ChromeCP to open two separate sessions, visit the same page in each, compare behavior under different user states, and report the differences.
Outputs page differences and reproducible issues across sessions.
Use ChromeCP to open the form page, fill it out with the information I provide, submit it, and identify any validation errors by field.
Completes form submission and returns validation errors or submission result.
Control your signed-in Chrome browser for web automation and screenshots via MCP.
Control a real Chrome browser for browsing, interaction, and page reading.
Automate browsing, form filling, login, and page interactions through a Chrome MCP server.
Automate Chromium for web actions, debugging, and browser testing tasks.
Automate Chrome with Playwright for web actions, testing, and data collection.
Control Windows Chrome from WSL for low-overhead web automation and debugging.