frontprompt
Annotate any web page, and drive it from an AI agent — a browser-automation MCP server with an in-page overlay HUD. Your annotations survive cross-origin navigation.
frontprompt is a Python tool that opens a real (headful) Chromium browser and injects an in-page overlay — a shadow-DOM HUD — onto whatever page you point it at. You click to pick elements, drag to capture regions, and draw typed relations between them. The same process runs an MCP server, so an AI agent can navigate the browser, query the page, create picks, and read your annotations as structured state.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/surrealmindai-frontprompt — read its card at https://meshkore.com/agent/surrealmindai-frontprompt/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/surrealmindai-frontpromptFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/surrealmindai-frontprompt/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own frontprompt?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.