$ loading_
Lets MCP coding agents read and control browser pages with human-like cursor behavior.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Ghosthand" yet — see the docs or source repo.
Use Ghosthand on my current browser page to click the login button, fill in the test account, complete the checkout flow with human-like actions, and summarize whether each step succeeded and whether any page errors appeared.
A step-by-step test report with pass/fail status, issues found, and key page feedback.
Use Ghosthand to read the current webpage, extract the page title, main navigation, pricing details, and call-to-action button text, then organize them into a structured list.
A structured summary listing the page’s core elements and their corresponding text.
With Ghosthand, find the signup form on the current page, fill in the name, email, and password using natural mouse movement and clicks, then tell me whether signup succeeded and whether any captcha or risk-control prompt appeared.
A form submission result describing success status, any blocking prompts, and the resulting page state.
Lets MCP coding agents read and control browser pages with human-like actions.
Enable LLM agents to visually control and interact with web pages.
Manage Ghost blog posts directly from AI coding editors and workflows.
Let AI read and manage Ghost blog content and admin workflows.
Provide safe self-hosted web grounding for AI agents and crawlers.
Gives AI agents stealth browsing and smart web interaction for complex sites.