get_canvas

MCP tool from Doop by kgoedecke

Canvas layout: every frame's position/size/meta

How to use it

Project documentation lists get_canvas for the Doop MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.

Install Doop

$claude mcp add --transport http doop http://localhost:4300/mcp

FULL DOOP LISTING

Other tools in Doop (15)

append_frame_html

Stream a design in chunks (start=true first, done=true last) — viewers watch it build up

create_canvas

Create a canvas, returns its shareable id

create_frame

Add a frame with HTML (auto-placed if no x/y)

delete_frame

Remove a frame

edit_frame_html

Targeted exact find/replace in a frame's HTML — morphs into the render in place

get_feedback

Fetch & claim open human feedback requests — for agents whose job is to poll the canvas periodically

get_frame

Read a frame including its HTML

get_frame_screenshot

Render the frame headlessly and return a PNG — lets agents see and iterate on their design

get_guide

The agent playbook — agents are instructed to load this first

import_webpage

Import one public URL onto a canvas as an editable HTML snapshot/frame

list_canvases

List all canvases

set_frame_html

Replace a frame's design in one shot — renders live for everyone

set_status

Broadcast a one-line "what I'm working on" — shown live in the working-now strip, avatar tooltip, and activity feed

update_frame

Rename / move / resize a frame

view_website

Inspect one public page read-only; returns a desktop screenshot and visible text without changing the canvas