tdmcp troubleshooting
SkillDev toolsDiagnose tdmcp and TouchDesigner bridge problems with bounded checks and evidence-backed recovery steps.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the tdmcp troubleshooting skill
What this skill tells your AI
The instructions your AI receives, as published by pantani/tdmcp in skills/curated/tdmcp-troubleshooting/SKILL.md and read by ahel’s review.
Use this skill when tdmcp cannot reach TouchDesigner, a structured operation fails, a node cooks with errors, or the observed network differs from the requested result.
Diagnose in layers
- Check local runtime status: package version, configuration source, bridge URL, authentication readiness, and whether the endpoint is reachable.
- If reachable, read bridge info and TouchDesigner build before testing mutating operations.
- Inspect the exact operator path, parameters, connections, cook errors, and preview relevant to the failure.
- Distinguish unsupported endpoint, invalid input, authorization failure, timeout, connection refusal, and TouchDesigner-side error. Do not collapse them into "offline".
- Reproduce with the smallest structured read or mutation. Do not use arbitrary Python merely to bypass a missing first-class operation.
Recovery boundaries
- Do not disable authentication or enable raw execution as a generic repair.
- Do not delete or overwrite artist content to make a health check pass.
- Preserve the configured bridge port; parallel analysis or test bridges must use isolated ports.
- After a repair, repeat the original bounded check and report both the prior failure and current evidence.
- If a check requires a running UI, hardware, pane, or saved project, mark it unverified when that dependency is absent.
Useful evidence includes exact endpoint status, typed error code, operator path, parameter name, TouchDesigner build, and the command or tool result that verified recovery. Redact tokens and project-sensitive content.
Signals
- GitHub stars
- 41
- Forks
- 9
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
tdmcp-troubleshooting- Source
- github.com/pantani/tdmcp