Add visual cursor to MCP browser tools - #1
Conversation
- Ported `PageCursor` from Python to TypeScript in `silentpilot/mcp_server/src/tools/cursor.ts`. - Integrated `PageCursor` into `silentpilot/mcp_server/src/tools/browser.ts`. - The cursor is now visible and animated during browser actions (click, type, scroll) performed by the agent. - Ensures the cursor is re-injected upon navigation or page reload. Co-authored-by: ansht3 <43502767+ansht3@users.noreply.github.com>
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with New to Jules? Learn more at jules.google/docs. For security, I will only act on instructions from the user who triggered this task. |
- Ported `PageCursor` from Python to TypeScript in `silentpilot/mcp_server/src/tools/cursor.ts`. - Integrated `PageCursor` into `silentpilot/mcp_server/src/tools/browser.ts`. - The cursor is now visible and animated during browser actions (click, type, scroll) performed by the agent. - Ensures the cursor is re-injected upon navigation or page reload. - Added `silentpilot/mcp_server/verify_cursor.ts` for verification. Co-authored-by: ansht3 <43502767+ansht3@users.noreply.github.com>
1 participant
This PR adds a visual cursor overlay to the browser automation tools provided by the MCP server.
It ports the
PageCursorlogic from the Pythonactionsmodule to the TypeScriptmcp_server. The cursor is injected into the page and animates smoothly to target elements before clicking or typing, providing visual feedback for the agent's actions. It also handles scrolling by moving the cursor to the center of the viewport.The cursor implementation is robust to page navigations and dynamic updates, ensuring it remains visible across multiple steps decided by the agent.
PR created automatically by Jules for task 4607269914451587551 started by @ansht3