What is blender-chatgpt-mcp AGENTS.md?

Repository instructions for blender-chatgpt-mcp, which connects an AI client to Blender, a 3D creation application, through an MCP server and a Blender add-on. They describe the architecture, commands, coding rules, and security requirements.

For guiding development, building, linting, testing, packaging, and integration work across the TypeScript MCP server, Python Blender add-on, and their local bridge.

They help coding agents make changes that fit the project's connection model, Blender's main-thread requirements, supported version, and validation process.

How bakaroart/blender-chatgpt-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to bakaroart/blender-chatgpt-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/bakaroart/blender-chatgpt-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/bakaroart/blender-chatgpt-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/bakaroart/blender-chatgpt-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/bakaroart/blender-chatgpt-mcp/agents-md)

Your own site

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

Per session 528 This file is loaded in full into every session.

When invoked 528 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	$0.00528	$0.00528
Opus 5.5	$0.00211	$0.00211
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash 16a6874ebc25, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blender-chatgpt-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 2mo 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

blender-chatgpt-mcp Agent Notes

Architecture

Codex connects directly to the local TypeScript Streamable HTTP MCP server at 127.0.0.1:3000/mcp; ChatGPT connector setups can reach the same endpoint through Secure MCP Tunnel. The MCP server validates tool inputs with Zod, sends authenticated JSON envelopes to the Blender bridge at 127.0.0.1:8765, and returns MCP structuredContent plus concise text. The Blender add-on runs a standard-library ThreadingHTTPServer; HTTP worker threads authenticate, parse, validate, and enqueue only. Blender API calls happen from the bpy.app.timers queue drain on Blender's main thread.

Commands

npm install
npm run dev
npm run build
npm run start
npm run lint
npm run typecheck
npm test
npm run test:integration
npm run test:blender
npm run package:addon
npm run check

Coding Conventions

Keep TypeScript strict and avoid any.
Keep pure Python modules importable without bpy.
Use fixed operation names and typed schemas only.
Target Blender 5.1+ behavior; do not claim older Blender compatibility without tests.
Prefer Blender data APIs; use bpy.ops only for narrow operations that need Blender context.
Keep bridge responses structured and stable.

Security Invariants

No arbitrary Python, shell, Blender operator, module, property-path, or generic attribute execution.
Bridge binds only to 127.0.0.1.
MCP defaults to 127.0.0.1; non-loopback bind is development-only and unsupported for public deployment.
Every bridge command requires a bearer token compared with constant-time comparison.
File writes stay under the configured Blender project root.
Do not log tokens, raw environment values, base64 image bodies, prompt text, or full scene dumps.
Mutations are never retried automatically after ambiguous failures.
Do not add OpenAI API calls or OPENAI_API_KEY requirements. Codex usage should work through ChatGPT/Codex sign-in and plan quota; BLENDER_BRIDGE_TOKEN is only a local bridge token.

Read the full file on GitHub · 44 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.

2mo ago First seen · 44 lines · 528 tokens per session scan A 16a6874ebc25

Subscribe to this mod's changes

blender-chatgpt-mcp AGENTS.md is an instructions file published in the GitHub repository bakaroart/blender-chatgpt-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 528 tokens to every session, about $0.0021 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 2026-08-31.

Creative and media

blender-chatgpt-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
blender-chatgpt-mcp AGENTS.mdbakaroart/blender-chatgpt-mcp	Instructions file	1	4mo ago	MIT	A	528	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

blender-chatgpt-mcp: Instructions file for Codex