Async Render Example (issue #317)

SkillMedia

Example skill, demonstrates async execution affinity: long-running tools surface as deferredHint=true in MCP tools/list. Use as a reference when writing domain skills with render or simulation tools. Not intended for production use.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Async Render Example (issue #317) skill

What this skill tells your AI

The instructions your AI receives, as published by dcc-mcp/dcc-mcp-core in examples/skills/async-render-example/SKILL.md and read by ahel’s review.

This skill demonstrates the execution and timeout_hint_secs fields added for issue #317. Tools are declared with either execution: sync (default) or execution: async; the MCP server derives the deferredHint annotation from this value and surfaces timeout_hint_secs under _meta.dcc.timeoutHintSecs on the tool definition (never inside annotations).

Behaviour

  • render_frames → execution: async + timeout_hint_secs: 600 → tools/list entry gets "annotations": { "deferredHint": true, ... } and "_meta": { "dcc": { "timeoutHintSecs": 600 } }.
  • quick_status → no execution field → default Sync → "annotations": { "deferredHint": false, ... } and no _meta.

Script convention

Each script reads JSON parameters from stdin and writes a JSON result to stdout — the standard dcc-mcp-core skill script contract.

Signals

GitHub stars
48
Forks
4
Last commit
Oct 2026
Advanced
Item type
skill
Key
async-render-example
Source
github.com/dcc-mcp/dcc-mcp-core