This is a proper Blender export workflow codified into a skill. It walks you through the full pipeline from scene inspection via MCP tools to headless GLTF export to gltf-transform optimization, which matters because the MCP server times out on export operations and procedural materials silently vanish. The material extraction script catches Color Ramps and procedural textures before you lose them, and the export flags prevent Array modifiers from ballooning your file from 1 MB to 56 MB. Use this if you're shipping Blender scenes to Three.js or React Three Fiber and tired of debugging why your materials look broken or your GLB is inexplicably huge.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
5
skills.sh installs
2.5K
GitHub stars
9
last updated
Aug 21, 2026

Install

$ npx -y skills add vladmdgolam/agent-skills --skill blender-mcp --agent claude-code

Installs into .claude/skills of the current project.

Files

Blender MCP

Tool Selection

Use structured MCP tools (get_scene_info, screenshot) for quick inspection.

Use execute_python for anything non-trivial: hierarchy traversal, material extraction, animation baking, bulk operations. It gives full bpy API access and avoids tool schema limitations.

Use headless CLI for GLTF exports — the MCP server times out on export operations.

Health Check (Always First)

  1. get_scene_info — verify connection (default port 9876)
  2. execute_python with print("ok") — verify Python works
  3. screenshot — verify viewport capture works

If MCP is unresponsive, check that the Blender MCP addon is enabled and the socket server is running.

Complete Export Workflow

This is the end-to-end linear narrative. Follow these steps in order. Do not skip steps.

Step 1: Health Check

Confirm MCP is alive before touching anything else:

# In MCP tool call:
get_scene_info
execute_python: print("ok")
screenshot

If any step fails, stop and fix MCP connectivity first. See Known Errors.

Step 2: Inspect Scene

Run the full hierarchy extraction to understand what you're working with:

Sponsors

Details

Repository
github.com/vladmdgolam/agent-skills
Categories
DevOps & CI/CD, Documentation, AI & Agent Building, Debugging, Automation & Workflows, Python, Sales & Marketing, Design & UI/UX, CLI & Terminal
First seen
May 16, 2026
1calm-north avatarrank-localcalm-north/seojuice-skillsBuild a local SEO strategy covering Google Business Profile, local citations, reviews, and NAP consistency. Use when the user asks about local SEO, Google Busin2.5Kskills.sh installs
2anthropics avatarcompetitive-analysisanthropics/financial-servicesFramework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user ask2.5Kskills.sh installs
3cursor avatarcontrol-uicursor/pluginsBuild or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots,2.5Kskills.sh installs
4browserbase avatarbrowserbase-clibrowserbase/skillsUse the Browserbase CLI (`browse`) for Browserbase Functions and platform API workflows. Use when the user asks to run `browse`, deploy or invoke functions, man2.5Kskills.sh installs
5getsentry avatarsentry-sdk-skill-creatorgetsentry/sentry-for-aiCreate a complete Sentry SDK skill bundle for any platform. Use when asked to "create an SDK skill", "add a new platform skill", "write a Sentry skill for X", o2.5Kskills.sh installs
6forcedotcom avatarorchestrating-datacloudforcedotcom/sf-skillsSalesforce Data Cloud product orchestrator for connect→prepare→harmonize→segment→act workflows. Use this skill when the user needs a multi-step Data Cloud pipel2.5Kskills.sh installs