"Canvas" matching MCP servers:

MCP server that lets AI agents control Perssona. It enables creating terminals, managing canvas nodes, sending prompts, and running multi-agent workflows.

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

Enables Codex to send structured data and render compact canvas artifacts beside native answer text on Even Realities G2 glasses, using authenticated stdio or Streamable HTTP transport with strict schemas, revisions, expiry, and delivery receipts.

A shared whiteboard for you and your AI agent I wanted my AI agent and me to be able to point at the same thing. Any MCP-capable agent can read the canvas, draw on it, drop thought bubbles, animate elements, and react when you sketch something.

Self-hosted, source-available AI workflow automation platform. Build multi-agent, RAG, and tool-using pipelines on a visual canvas and publish any workflow as an MCP server (stdio/SSE/Streamable HTTP). Also an MCP client via the agent node.

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.