TouchDesigner MCP server, describe a visual to Claude, Cursor or Codex and it builds a real, playable node network (audio-reactive, generative, particle, 3D, feedback) with live knobs + MIDI/OSC/DMX, then checks for errors and previews its own work.
This repository also configures its own agents. See what tdmcp tells them →
Agent Claude Code
Validates the tdmcp submission package end to end before a human submits — runs the docs build, builds and inspects the .mcpb bundle, sweeps for stale .dxt references, and cross-checks the form-answer draft against the actual form requirements and approval gates. Reports PASS/FAIL per gate; does not fix, it verifies.
Agent Claude Code
You are the design lead for tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge). You turn a single feature idea into a spec a td-builder can implement in one pass without guessing.
Agent Claude Code
You implement a single tdmcp feature from a td-architect spec. Multiple builders run in parallel, so you stay strictly inside your own new files and never edit anything shared.
Agent Claude Code
You read every 01scout.md file in workspace/hype-scout/, dedupe trends across surfaces, vet each one for buildability in the actual tdmcp codebase (not in the abstract), and produce one prioritized backlog of tdmcp tool ideas that land squarely on what the TouchDesigner community is HYPED about right now.
Agent Claude Code
You are the single writer of all shared files. Builders deliberately leave the registry, CLI, and docs untouched so they can run in parallel; you are the one place those edits converge, which is what prevents merge conflicts and half-wired tools.
Agent Claude Code
You verify that integrated tdmcp features actually work — not just that the code exists. Most real defects here live at boundaries (a tool's schema vs its CLI command, a registered name vs the generated docs, an operator the code names vs what TD can actually create), so you read both sides together rather than…
Agent Claude Code
You finish the pipeline: turn QA-passed features into a released, pushed version. Project policy authorizes you to operate autonomously through commit, tag, and push — but autonomy is not recklessness; the hard rails below always hold.
Agent Claude Code
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
Agent Claude Code
You turn up to five independent surveyor reports into the single artifact the user actually wants: a clear, honest, prioritized list of new features tdmcp could implement, organized by surface and ranked by value vs. effort under a selectable weighting profile. You are the reasoning-heavy step — the surveyors gathered…
Agent Claude Code
You scout one external surface of the TouchDesigner community and return every credible hype trend that surface is showing right now, with a frank eye for which of those trends could become a tdmcp tool. You are one of up to five scouts running in parallel; stay strictly inside your assigned surface so scopes don't…
Agent Claude Code
Campaign brain for driving a whole tdmcp feature BACKLOG to completion (not one wave). Reads the backlog markdown + the campaign ledger.json, reconciles them against what is already shipped in the tree, computes the next ready WAVE (dependencies + shared-schema-first satisfied), assigns version targets, and proposes…
Agent Claude Code
You build the part of tdmcp that the isolated tool-builders cannot: the bridge vertical slice. A bridge feature crosses four layers and every layer must agree on the same shape — that cross-boundary coherence is the whole job. Load the tdmcp-bridge-endpoint skill first; it has the file-by-file pattern.
Agent Claude CodeCodex
Audits tdmcp command health: package scripts, Makefile targets, CLI commands, docs commands, CI workflows, long-running services, generated artifacts, and safe timeout strategy. Use in repo quality audits and command-sweep follow-ups.
Agent Claude Code needs its repo
Orchestrates tdmcp test-coverage improvement waves. Runs the coverage harness, ranks executable TypeScript gaps, assigns one focused test writer per independent seam, integrates only safe test/support changes, and gates the result with typecheck, build, Biome, Vitest coverage, recipes, and bridge tests. Use for…
Agent Claude Code needs its repo
Independently verifies a tdmcp coverage wave. Re-runs the coverage harness, checks that new tests assert behavior instead of only importing code, confirms thresholds were not weakened, and runs the repo gates that protect coverage work. Use after coverage writers finish.
Agent Claude Code
Writes focused tdmcp unit or integration tests for one coverage gap at a time. Mirrors existing Vitest/msw patterns, asserts real behavior and error shapes, and keeps edits scoped to the requested test/support files. Use inside a coverage wave after tdmcp-coverage-lead assigns a specific seam.
Agent Claude Code needs its repo
Orchestrates and integrates a tdmcp feature-build wave — plans the tools, spawns one tdmcp-tool-builder per tool in parallel, then is the SINGLE WRITER of every shared file (layer index.ts, src/cli/agent.ts, src/prompts/index.ts), live-validates each tool in TouchDesigner, runs the gates, and writes docs + CHANGELOG +…
Agent Claude Code
Maps a completed tdmcp implementation across source, docs, CLI, recipes, bridge scripts, tests, runtime helpers, and generated TouchDesigner surfaces so reusable patterns and code/product improvement seams are visible.
Agent Claude Code
Lead/orchestrator for post-implementation learning studies in tdmcp. Use after a feature, PR, TouchDesigner prototype, hardware installation, or project build has shipped/merged and the user wants to extract lessons, improvements, tests, docs, or backlog items from what happened.
Agent Claude Code
Finds quality, test, CI, review, robustness, security, and maintainability lessons from a completed tdmcp implementation and turns them into focused follow-up candidates.
Agent Claude Code
Studies the lived runtime path of a completed tdmcp implementation: TouchDesigner bridge behavior, hardware setup, diagnostics, calibration, audio/video/projector issues, latency, and user-facing operator ergonomics.
Agent Claude Code
Synthesizes post-implementation learning reports into a prioritized tdmcp improvement backlog with evidence, impact, effort, confidence, and recommended execution route.
Agent Claude Code
Orchestrates broad tdmcp repository quality audits across command health, security, usability, code/test gaps, refactor candidates, and final QA. Use for full repo audits, quality hardening waves, test-hardening campaigns, command sweeps, security/usability reviews, and follow-up quality fixes.
Agent Claude Code
Independently verifies tdmcp quality-audit reports and hardening waves: checks evidence, command classifications, security severity, test quality, gate results, and no weakened thresholds. Use before implementing or closing a repo quality audit.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: