What is td-mcp AGENTS.md?

Repository instructions for td-mcp, a server that lets an AI client inspect and control TouchDesigner projects. TouchDesigner is a tool for creating real-time interactive visuals, and these instructions describe the server's code, safety rules, and commands.

Use them when building, testing, or modifying td-mcp, including its MCP tools, web dashboard, safety checks, or TouchDesigner connection.

They give a coding agent the project context it needs before changing the repository. This reduces mistakes about file locations, testing, and scripts that communicate with a running TouchDesigner project.

How Gleinkaa/td-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Gleinkaa/td-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Gleinkaa/td-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Gleinkaa/td-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gleinkaa/td-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/gleinkaa/td-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gleinkaa/td-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gleinkaa/td-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gleinkaa/td-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gleinkaa/td-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,492 This file is loaded in full into every session.

When invoked 1,492 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01492	$0.01492
Opus 5.5	$0.00597	$0.00597
Sonnet 5.5	$0.00298	$0.00298
Haiku 4.5	$0.00149	$0.00149

Measured 23d ago against content hash 08730a642689, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

td-mcp AGENTS.md 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 23d 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.

AGENTS.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — td-mcp

What this repo is

An MCP server plus a web dashboard for TouchDesigner. Claude Code (or any MCP client) talks stdio to this server, which talks HTTP to a WebServer DAT inside a running TD project on port 9981; a FastAPI dashboard on :8080 exposes the same tooling in a browser. 22 MCP tools across four groups — inspect (list ops, trace signal flow, read CHOPs, read/set params), optimize (cook-time stats, hotspots, unused ops), cleanup (find bypassed/dead ops, delete with dry-run default, validate network) and templates (5 built-in CHOP recipes plus a DAW mapping generator for OSC/MIDI CC). Every script that reaches TD goes through src/td_mcp/safety.py first.

Layout (real paths)

pyproject.toml                    Hatchling package; scripts td-mcp and td-mcp-web; pytest config
src/td_mcp/server.py              FastMCP stdio server — the 22 tools
src/td_mcp/web.py                 FastAPI + htmx dashboard (main() runs uvicorn on :8080)
src/td_mcp/td_client.py           Async httpx client to the TD WebServer DAT; never raises
src/td_mcp/safety.py              The script validator (blocks imports, eval/exec, dunders, obfuscation)
src/td_mcp/models.py              Pydantic models
src/td_mcp/tools/inspect.py       List ops, trace signal flow, read CHOPs and params
src/td_mcp/tools/optimize.py      Cook-time hotspots, unused/dead-end ops, suggestions
src/td_mcp/tools/cleanup.py       Dead/bypassed ops, delete_operator, cleanup_dead_ops, validation
src/td_mcp/tools/templates.py     5 CHOP recipes + the DAW mapping generator
td/webserver_callbacks.py         Drop-in for TD's WebServer DAT onHTTPRequest callback
tests/test_models.py, test_safety.py, test_server.py, test_td_client.py, test_tools.py

How to build / run / test

Requires Python 3.10+.

pip install -e ".[dev]"
pytest                                    # asyncio_mode=auto, testpaths=["tests"] (26 tests)

td-mcp                                    # MCP server over stdio
td-mcp-web                                # dashboard at http://localhost:8080
uvicorn td_mcp.web:app --port 8080 --app-dir src   # same dashboard, run directly

Read the full file on GitHub · 103 lines

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.

23d ago First seen · 103 lines · 1,492 tokens per session scan A 08730a642689

Subscribe to this mod's changes

td-mcp AGENTS.md is an instructions file published in the GitHub repository Gleinkaa/td-mcp (0 stars, last pushed 24d ago), licensed MIT. It adds 1,492 tokens to every session, about $0.0060 per session on Opus 5.5. 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 2026-10-16.

Creative and media

td-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
td-mcp AGENTS.mdGleinkaa/td-mcp	Instructions file	0	24d ago	MIT	A	1,492	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

td-mcp: Instructions file for Codex