Skip to content
TrustedSkillsbeta
Back to all skills

Blender Mcp

Checked
vladmdgolam·vlatest·agents·MIT

Provides MCP tools guidance and assistance for orchestrating AI agents and multi-step workflows.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

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

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

vladmdgolam

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned vladmdgolam/agent-skills at 5e3e9b95ec.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
5e3e9b95ec
Manifest
skills/blender-mcp/SKILL.md
Scanned
4 files, 1,293 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill, Blender MCP, provides tools and guidance for AI agents interacting with Blender through the Model Context Protocol (MCP). It enables agents to inspect a Blender scene, extract its hierarchy and material information, and perform non-trivial operations using Python scripting within Blender's environment. Specifically, it facilitates automated workflows like GLTF exports by leveraging the bpy API and handling potential timeout issues associated with lengthy export processes.

When to use it

  • Automated Scene Inspection: Quickly assess a Blender scene’s structure and content before performing modifications or exporting.
  • GLTF Export Workflows: Handle complex GLTF export operations that might time out using standard MCP tools.
  • Material Verification: Identify missing or problematic materials within a Blender scene to ensure correct exports.
  • Scene Hierarchy Traversal: Extract and analyze the entire object hierarchy of a Blender scene for reporting or further processing.

Key capabilities

  • Structured Tool Selection: Provides pre-defined MCP tools like get_scene_info (for connection verification) and screenshot (for viewport capture).
  • Python Scripting via execute_python: Allows running arbitrary Python code within Blender, granting full access to the bpy API.
  • Headless CLI for GLTF Exports: Facilitates GLTF exports using a command-line interface to avoid MCP timeout issues.
  • Scene Hierarchy Extraction: Extracts detailed information about objects including name, type, location, rotation, scale, visibility, vertex count and material assignments.

Example prompts

  • "Run get_scene_info to check the Blender connection."
  • "Execute Python: print("ok") to verify Python execution within Blender."
  • "Use execute_python to extract the scene hierarchy and print it as JSON."

Tips & gotchas

  • Health Check First: Always start with a health check (using get_scene_info, execute_python: print("ok"), and screenshot) to ensure MCP connectivity before attempting any other operations.
  • Python for Complexity: For anything beyond simple inspection, leverage the execute_python tool to access Blender’s full API.
  • GLTF Exports Timeout: Use the headless CLI method for GLTF exports as standard MCP calls may time out during these lengthy processes.