| name | agent-vision-diagrams |
| description | Create and iterate on shareable visual diagrams (architecture maps, flowcharts, state machines, class/domain models, mindmaps, dependency maps) via the Agent Vision MCP server or its HTTP action API. Use when the user asks for a diagram, visualization, or "draw this out" during a conversation, or when the user hands you an Agent Vision app URL + connection token. |
Agent Vision — diagrams for the user
Agent Vision is a hosted diagram app. You write a small JSON document (the
spec — a DSL), the app renders it (2D now, isometric later), stores every
change as an immutable revision, and returns a public share URL plus a
rendered PNG so you can show the user immediately.
This installed skill is a thin connection recipe. The full DSL, the color /
idiom grammar, worked examples, ops-patch reference, icon catalog, and warning
list live in the hosted, canonical skill doc — fetch it once at the start of a
diagramming session and follow it:
<app-url>/skill.md (ask the user for their Agent Vision app URL)
(Replace the host with whatever app URL the user gave you; the skill doc lives
at <app-url>/skill.md.)
Connecting (given only the user's app <url>)
Step 0 — check the environment first: if AGENT_NATIVE_VISION_URL and
AGENT_NATIVE_VISION_TOKEN env vars are set (provisioned containers), use them
and skip all auth below — bearer header on every call, done.
Primary — device flow, you drive it. No pre-minted token, no password:
POST <url>/_agent-native/mcp/connect/device/start (empty JSON body, no
auth) → { device_code, user_code, verification_uri_complete, interval, expires_in }.- Tell the user in chat: "Open
<verification_uri_complete> and click
(code )." Any device where they're
already logged in works.
