WebMCP Agent

A browser assistant that reads the current page, takes files and images, and uses the page's WebMCP tools with your own model.

WebMCP Agent is a browser assistant in Chrome's side panel that works with the AI model you choose. • Ask about the current page. It reads the page's visible text, so you can summarize, explain, or extract information. • Attach files and images, or paste a screenshot straight into the message box. • Use page tools. On sites that provide WebMCP tools, the model can look things up and take actions for you. Anything that changes the page asks for your approval first. • Skills. Save instructions for tasks you repeat and pick one by typing /, or let the model use it when it fits. Import and export SKILL.md files. • Diagrams. Flowcharts, sequence diagrams, and other Mermaid diagrams in answers are drawn in place; enlarge them or save them as SVG or PNG. • Bring your own model. Connect any OpenAI-compatible Chat Completions endpoint, such as DeepSeek or OpenAI, with your own API key. • Side panel or floating window. Move the conversation into its own window and back whenever you like. • Follows Chrome's light and dark themes, in English and Simplified Chinese. Privacy: there is no server of its own. Your messages, page content, and attachments go only to the model endpoint you configure. Conversations are cleared when Chrome closes.