"Canvas" matching MCP servers:

Enables MCP clients to operate a RunningHub infinite canvas through a local bridge and Chrome extension using the current logged-in session: reading nodes and prompts, cloning templates, laying out and connecting nodes, uploading images/audio/video, submitting generation, and archiving outputs. Supports both the international (www.runninghub.ai / rhtv.runninghub.ai) and China sites, with dry-run previews and revision-checked edits.

Local-first Figma MCP server providing unlimited read access via Personal Access Token, HTML replica generation with parity verification, and write-to-canvas through a companion plugin bridge.

Enables AI agents to inspect and edit the live browser-resident canvas of the Boarderless app via a structured spatial ledger.

Enables AI assistants to inspect values, view errors, and capture canvas output from Observable Notebook Kit notebooks running in a web browser.

Exposes OpenClaw tools (web search, page fetching, browser automation, PDF analysis, messaging, inter-agent communication, Canvas) as MCP tools for ACP agents.

MCP server that connects AI assistants to a live Ketcher window, the open-source web-based chemical structure editor. Draw, edit, and organize structures directly in the canvas you have open.

Enables MCP clients to control a canvas-based macOS browser for web development, allowing agents to open and interact with live pages, capture screenshots, measure elements, and manage local project workflows.

Modular testing and automation MCP servers for Android devices, desktop browsers, canvas games, and visual regression.

Lets a local Claude Code session drive a visible browser paint editor through four tools — viewing a canvas screenshot, laying down a single brush stroke with real color/size controls, undo/redo, and exporting the finished PNG — so the model can draw an uploaded reference portrait stroke by stroke. Supports optional recording and run-limit settings for comparing drawing quality, timing and CLI cost between a standard and a cost-controlled setup.

Enables LLMs to read, query, search, and manipulate a live schematic or PCB canvas in the browser, including retrieving the active document, searching the LCSC parts database, and placing components, drawing wires, and updating net names. Bridges an MCP client to the editor via a WebSocket extension so changes appear in real time.