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.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.AGENT_TRIGGER_DEBOUNCE_MS— (default 3000)ANTHROPIC_API_KEY— (required for vision tools only - others may be used)ANTHROPIC_AUTH_TOKENGRID_CELL_SIZEMCP_WS_PORT— (default 3002)NAPKIN_COMPACT_TRIGGERS— (true/false, default false)NAPKIN_DEFAULT_FONT_FAMILYNAPKIN_EXPORT_DIR— (optional base dir for relative exports)NAPKIN_INSTRUCTIONS_PROFILENAPKIN_MCP_PORT— (default 3003)NAPKIN_SESSION_PATHNAPKIN_SESSION_TTL_MS— (default 7200000)NAPKIN_TRANSPORT— (http or stdio, default http)NAPKIN_TRIGGER_INCLUDE_CANVAS— (true/false, default false)NAPKIN_TRIGGER_SEMANTIC_ONLYNAPKIN_TRIGGER_WEBHOOK— OpenClaw — built in. Set in your environment and it routes automatically.NAPKIN_VISION_MAX_TOKENSNAPKIN_VISION_MODELNAPKIN_WEBHOOK_DISABLEDPROXIMITY_CONFIDENCE_THRESHOLD[](https://m8ven.ai/mcp/sshwarts-napkin-1wlnt3)