blender-ai-mcp: Instructions file for Codex

AGENTS.md

blender-ai-mcp AGENTS.md is an instructions file for Codex, OpenCode from PatrykIti/blender-ai-mcp. It costs 5,297 tokens per session, scanned A, original, Apache-2.0.

A project instruction guide for Blender AI MCP, a system that lets language models control Blender through a structured tool interface. It explains the split between the server, the Blender plug-in, and the routing layer.

In plain words
What is it for?
Use it to navigate the repository, add or change Blender automation tools, route tool calls, and maintain the server-to-Blender communication boundary.
Why use it?
It helps developers keep tool definitions, routing, network communication, and Blender operations in the correct layers instead of mixing responsibilities.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is PatrykIti/blender-ai-mcp's own configuration. It tells Codex and OpenCode how to work on blender-ai-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything blender-ai-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PatrykIti/blender-ai-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/PatrykIti/blender-ai-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/PatrykIti/blender-ai-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.

agentmods badge for blender-ai-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/patrykiti/blender-ai-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/patrykiti/blender-ai-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/patrykiti/blender-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/patrykiti/blender-ai-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.

agentmods 80×15 button for blender-ai-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/patrykiti/blender-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/patrykiti/blender-ai-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,297 This file is loaded in full into every session.
When invoked 5,297 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.05297 $0.05297
Opus 5 $0.02648 $0.02648
Sonnet 5 $0.01059 $0.01059
Haiku 4.5 $0.00530 $0.00530

Measured 10d ago against content hash 000231500455, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

blender-ai-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 10d 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 · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project Purpose

blender-ai-mcp is a split Blender control system for LLMs:

  • server/ exposes FastMCP tools and translates them to RPC calls.
  • blender_addon/ runs inside Blender and executes the actual bpy operations.
  • server/router/ is a supervisor layer that corrects, expands, and routes LLM tool calls through metadata and workflows.

The project exists to avoid raw-code Blender automation. The intended product surface is a stable, deterministic tool API with strong inspection, recovery, and workflow support.

Repo Map

  • server/domain/: abstract tool interfaces and core models. Keep framework-free.
  • server/application/tool_handlers/: RPC-backed application handlers that implement domain interfaces.
  • server/adapters/mcp/areas/: FastMCP tool definitions grouped by area.
  • server/adapters/rpc/: socket RPC client used by handlers.
  • server/infrastructure/: DI and config.
  • server/router/: router, metadata, classifiers, workflow engine, vector store, and MCP integration helpers.
  • blender_addon/application/handlers/: Blender-side handlers using bpy.
  • blender_addon/infrastructure/rpc_server.py: threaded RPC server that schedules work safely on Blender's main thread.
  • tests/unit/: fast tests with mocked Blender/RPC.
  • tests/e2e/: Blender-backed end-to-end tests.
  • _docs/: canonical design/task/history docs. Read the area-specific docs before structural changes.

Architecture Rules

  • Preserve Clean Architecture direction: adapters -> application -> domain.
  • Do not import FastMCP, socket code, or Blender APIs into server/domain/.
  • Keep Blender-specific logic inside blender_addon/.
  • MCP adapters should stay thin. Business logic belongs in handlers or router components, not inside @mcp.tool wrappers.
  • Dependency wiring belongs in server/infrastructure/di.py.
  • Router additions must remain metadata-driven where possible.

Runtime Boundaries

Read _docs/_ROUTER/RESPONSIBILITY_BOUNDARIES.md before changing FastMCP integration, LaBSE usage, router policy, or verification flows.

Read the full file on GitHub · 390 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.

  1. 10d ago First seen · 390 lines · 5,297 tokens per session scan A 000231500455

Subscribe to this mod's changes

blender-ai-mcp AGENTS.md is an instructions file published in the GitHub repository PatrykIti/blender-ai-mcp (57 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,297 tokens to every session, about $0.0265 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens