implement-experimental

An implementation task for adding experimental-technique search tools to a TouchDesigner MCP Server. TouchDesigner is software for building interactive visuals, and MCP is a way for an assistant to call project tools.

In plain words
What is it for?
Use it to implement lookups by technique or category, search experimental techniques by query, filter results by minimum TouchDesigner version, and return technique details including code examples.
Why use it?
It makes experimental techniques easier to find and retrieve from categorized data instead of requiring manual browsing. The supplied task describes creating the tools and data access, not broader server behavior.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/bottobot/touchdesigner-mcp-server/implement-experimental
Clone the repo
git clone --depth 1 https://github.com/bottobot/touchdesigner-mcp-server

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00015 $0.00576
Opus 5 $0.00008 $0.00288
Sonnet 5 $0.00003 $0.00115
Haiku 4.5 $0.00002 $0.00058

Measured 2d ago against content hash fa1cd74e08ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-experimental scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/implement-experimental.md · 55 lines

What it actually says

You are implementing MCP tools for experimental TouchDesigner techniques.

Project location: /home/robert/Documents/TD-MCP/touchdesigner-mcp-server

Prerequisite: /wiki/data/experimental/ should have been populated by the previous research agent.

Tasks:

  1. Create /tools/get_experimental_techniques.js: InputSchema: { category: { type: 'string', enum: ['glsl','gpu-compute','machine-learning','generative-systems','audio-visual','networking','python-advanced'], required: false }, name: { type: 'string', description: 'Technique name to look up', required: false } } Logic: Load /wiki/data/experimental/{category}.json or search all categories if no category given Return: Full technique details including codeExample

  2. Create /tools/search_experimental.js: InputSchema: { query: { type: 'string', required: true, description: 'Search term for experimental techniques' }, version: { type: 'string', required: false, description: 'Filter by minimum TD version' } } Logic: Search across all experimental categories, return matching techniques

  3. Create /tools/get_glsl_pattern.js: InputSchema: { pattern: { type: 'string', required: true, description: 'GLSL pattern type (raymarching/reaction-diffusion/feedback/procedural)' }, includeCode: { type: 'boolean', required: false, default: true } } Logic: Return GLSL code examples and setup instructions from the glsl experimental data

  4. Add experimental operator data files to /wiki/data/processed/:

  • feedback_top.json (Feedback TOP — requires version 099+, key for generative systems)
  • noise_top.json (Noise TOP — procedural generation workhorse)
  • render_top.json (Render TOP — 3D scene rendering)
  • geo_comp.json (Geometry COMP — 3D geometry container)
  • script_top.json (ensure it exists with GPU compute info, don't overwrite if already comprehensive)
  • null_top.json (Null TOP — pass-through, debugging)
  • level_top.json (Level TOP — color grading and correction)
  • blur_top.json (Blur TOP — multiple blur algorithms)
  • transform_top.json (Transform TOP — 2D transformations)
  • composite_top.json (Composite TOP — blending modes)

For each operator file, include versionSupport field.

  1. Update /index.js to register: get_experimental_techniques, search_experimental, get_glsl_pattern

  2. Update /wiki/data/search-index/search-index.json to include all new experimental operators and techniques

Follow exact code patterns from existing tools for consistency.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 55 lines · 15 tokens per session scan A fa1cd74e08ec

Subscribe to this mod's changes

implement-experimental is an agent published in the GitHub repository bottobot/touchdesigner-mcp-server (76 stars, last pushed 14d ago), licensed MIT. It adds 15 tokens to every session and 576 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.