Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Blender Mcp Ops

FSecurity

Use when an AI agent must operate Blender 3D via the blender-mcp MCP server — setup, scene ops, materials, code execution, and the SVG-first cost-gate workflow. Triggers on \"Blender MCP\", \"blender-mcp\", \"uvx blender-mcp\", \"operate Blender\", \"SVG to mesh\", \"blender-mcp-ops\". Non-triggers: read-only rig/pose inspection (use blender-motion-state-inspection), image-to-Three.js/WebGL code (use img2threejs), Unreal/MetaHuman pipelines. Outcome: a working Blender+MCP loop that validates ...

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonshellawsgit

Works with

claude codecursorclimcp

Security Analysis

F34/100
criticalPipes output to a shell interpreter
mediumUses curl or wget to download content
criticalDownloads and executes remote scripts — classic supply chain attack
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill blender-mcp-ops --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Blender Mcp Ops?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Blender Mcp Ops
[![Security: F — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-blender-mcp-ops/badge)](https://www.skillsdirectory.com/skills/majinmagros-blender-mcp-ops)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: blender-mcp-ops
description: "Use when an AI agent must operate Blender 3D via the blender-mcp MCP server — setup, scene ops, materials, code execution, and the SVG-first cost-gate workflow. Triggers on \"Blender MCP\", \"blender-mcp\", \"uvx blender-mcp\", \"operate Blender\", \"SVG to mesh\", \"blender-mcp-ops\". Non-triggers: read-only rig/pose inspection (use blender-motion-state-inspection), image-to-Three.js/WebGL code (use img2threejs), Unreal/MetaHuman pipelines. Outcome: a working Blender+MCP loop that validates cheap (image/SVG) before spending tokens on meshes, with screenshots verifying every step."
metadata:
  origin: ECC
---

# Blender MCP Ops

Drive real Blender (not code that draws 3D) through the community
`blender-mcp` integration: an MCP server plus a Blender addon talking over a
local socket. Validated 2026-09-07 against
https://github.com/ahujasid/blender-mcp (third-party, not made by Blender).

## When To Activate

- The user wants the agent to model, edit, texture, or render in Blender.
- Image/SVG → 3D mesh workflows, scene assembly, material passes.
- `blender-mcp` install, connection, or tool errors.

## Setup (official quickstart)

1. Install `uv` with the **official installer** (not `pip install uv`):
   macOS `brew install uv`; Linux `curl -LsSf https://astral.sh/uv/install.sh | sh`;
   Windows `powershell -c "irm https://astral.sh/uv/install.ps1 | iex"`.
2. Register the MCP server (one instance only — never two clients at once):
   - Claude Code: `claude mcp add blender uvx blender-mcp`
   - Codex: `codex mcp add blender -- uvx blender-mcp`
   - Desktop/Cursor/VS Code: `{"command": "uvx", "args": ["blender-mcp"]}`
     (Windows GUI: `{"command": "cmd", "args": ["/c", "uvx", "blender-mcp"]}`).
   - OpenCode/Antigravity: same command with `BLENDER_HOST`/`BLENDER_PORT` env.
3. Install the addon: `uvx blender-mcp install-addon`, then Blender →
   Edit → Preferences → Add-ons → enable "Interface: MCP for Blender".
4. Connect: in the 3D viewport press `N` → "MCP for Blender" tab →
   Start MCP Server (default `localhost:9876`, env `BLENDER_HOST`/`BLENDER_PORT`).
5. Requirements: Blender 3.0+, Python 3.10+ (pin `--python 3.11` with
   `UV_PYTHON_PREFERENCE=only-managed` if conda/pyenv hijacks `uvx`).

## Capabilities

- Scene/object info, create/modify/delete objects, materials and colors.
- `execute_blender_code`: arbitrary Python in Blender — powerful, dangerous.
- Asset sources: Poly Haven (HDRIs/textures), Sketchfab, Poly Pizza low-poly
  (keys stored in addon preferences; ~69% of Poly Pizza needs attribution),
  Hyper3D Rodin / Hunyuan3D generated models.
- `BLENDER_MCP_SAFE_MODE=1` validates scripts before running (blocks file,
  process, network access; normal modeling still works). **Always save the
  .blend before executing generated code.**

## SVG-First Cost-Gate (mandatory)

Meshes and animation burn tokens. Never model blind:

1. **Image first**: concept art / sprite-sheet + lore; re-attach renders
   ("closer to the attachment") until the look converges.
2. **Cheap validation**: approve a short test scene or SVG before any mesh work.
3. **Mesh second**: SVG → mesh, materials, lighting — one pass at a time.
4. **Screenshot verify**: `get_viewport_screenshot` after every pass; fix from
   the screenshot, not from memory.
5. Long loops are normal (multi-hour to hit target fps/quality) — that is
   expected iteration, not failure.

## Troubleshooting

| Problem | Fix |

## Exemplo

```text
Pedido: "modela uma cadeira low-poly a partir deste SVG"
1) Valida barato: render de teste do SVG como plano + screenshot OK do usuário
2) Mesh: SVG → mesh, um passe de materiais, screenshot após cada passe
3) Seguro: .blend salvo antes de cada execute_blender_code; SAFE_MODE=1 ativo
Nunca: modelar 2h de mesh antes de validar o look no barato
```

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →