blender-mcp: Instructions file for Claude Code

CLAUDE.md

blender-mcp CLAUDE.md is an instructions file for Claude Code from kleer001/blender-mcp. It costs 389 tokens per session, scanned A, original, MIT.

Blender operating instructions for an agent connected through an MCP add-on, covering safe scene editing, naming, tool choice, and visual checks.

In plain words
What is it for?
Use them to inspect and modify Blender objects, materials, collections, transforms, and scenes, then capture the viewport to check visual changes.
Why use it?
They reduce mistakes when changing a 3D scene by requiring connection checks, orderly operations, descriptive names, and confirmation before destructive actions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kleer001/blender-mcp's own configuration. It tells Claude Code how to work on blender-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-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kleer001/blender-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/kleer001/blender-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kleer001/blender-mcp

Made for: Claude Code.

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-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kleer001/blender-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kleer001/blender-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kleer001/blender-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kleer001/blender-mcp/claude-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-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kleer001/blender-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kleer001/blender-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 389 This file is loaded in full into every session.
When invoked 389 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 $0.00389 $0.00389
Opus 5 $0.00195 $0.00195
Sonnet 5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 9d ago against content hash b54e0e9a3960, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

blender-mcp CLAUDE.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 9d 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.md · 39 lines

What it actually says

Blender MCP — AI Behavior Rules

Connection Protocol

  1. Ping before starting work. Call ping to verify the addon is reachable.
  2. Never rapid-fire commands. Wait for each response before sending the next.
  3. Separate scene setup from rendering. Do all scene modifications first, then render.
  4. Use batch for bulk operations. Executes atomically in a single undo step.
  5. If connection fails, stop. Do not retry in a tight loop. Tell the user to check the addon panel.

Naming Conventions

  • Use descriptive names: hero_cube not Cube.001
  • Materials: mat_red_plastic not Material.002
  • Collections: col_environment not Collection 3

Workflow Patterns

  • Always check before modifying. Use get_object_info or list_objects before operating on objects.
  • Prefer dedicated tools over execute_python. Only use execute_python when no dedicated tool exists.
  • Capture viewport after visual changes. Call capture_viewport to verify results.
  • Use set_transform for positioning. Don't use execute_python for simple transforms.

Destructive Actions

Confirm with the user before:

  • Deleting objects, materials, or collections
  • Loading a new file (replaces current scene)
  • Executing arbitrary Python code
  • Baking simulations (long-running, irreversible)

Blender-Specific Notes

  • Object names auto-increment (.001, .002) if duplicates exist. Always use the returned name.
  • Blender uses Z-up coordinate system. Y is depth, Z is height.
  • Frame 1 is the default start frame, not frame 0.
  • Rotation is in radians in the API, degrees in the UI.
  • Material slots are 0-indexed. An object can have multiple slots.
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. 9d ago First seen · 39 lines · 389 tokens per session scan A b54e0e9a3960

Subscribe to this mod's changes

blender-mcp CLAUDE.md is an instructions file published in the GitHub repository kleer001/blender-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 389 tokens to every session, about $0.0019 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 2026-08-31.

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens