Meshy 3D Agent

AI agent skills for the Meshy AI 3D generation platform. Enables AI coding assistants (Cursor, Claude Code, OpenClaw) to generate 3D models, textures, images, rig characters, animate them, and prepare models for 3D printing — no MCP server required.

New Updates: For new web agent experience, come to try out our new Meshy Workspace Agent! It supports:

• :brain: Brainstorm with you, pitching directions first
• :art: Generate visuals in batches, refined through chat
• :ice_cube: Turn your favorite into 3D — print, download, anywhere
• :books: Answer your 3D questions in-line

How It Works

These are agent skills — no server, no MCP process. Each skill bundles a small Python CLI (scripts/) plus on-demand markdown references (references/), and your AI assistant reads the skill files and drives the Meshy API directly through the bundled scripts.

Skills

meshy-3d-generation (core)

Full 3D generation lifecycle: API key setup, task creation, polling, downloading, and multi-step pipelines.

meshy-3d-printing (optional)

3D printing workflow: slicer detection, automated printability analysis & repair, white model printing, multicolor printing via API.

The printing skill bundles the same task-runner CLI as the generation skill and shares its environment setup.

meshy-openclaw (OpenClaw / ClawHub)

A single unified skill for the OpenClaw ecosystem. Combines generation + printing into one self-contained skill, with OpenClaw-compatible metadata.clawdbot frontmatter and a full SECURITY MANIFEST.

Designed for ClawHub publishing. API key is stored only in .env in the current working directory — no shell profile access.

Quick Install

One command to install all skills:

npx skills add meshy-dev/meshy-3d-agent

Then set your API key (pick any method below):

Or simply start using the skill — when the agent loads it, it will detect that no API key is configured, ask you for it, and set it up for the current session (it never writes your key anywhere except .env on your request).

nano ~/.zshrc

export MESHY_API_KEY="msy_YOUR_API_KEY"

source ~/.zshrc

echo 'MESHY_API_KEY=msy_YOUR_API_KEY' > .env

$env:MESHY_API_KEY = "msy_YOUR_API_KEY"

MESHY_API_KEY=msy_YOUR_API_KEY

Prerequisites

• A Meshy API key (get one here — requires Pro plan or above)
• Python 3 with requests package (pip install requests)

Manual Installation

npx clawhub install meshy-dev/meshy-3d-agent

mkdir -p .cursor/skills

# Core (required)
cp -R skills/meshy-3d-generation .cursor/skills/

# 3D Printing (optional)
cp -R skills/meshy-3d-printing .cursor/skills/

mkdir -p .claude/skills

# Core (required)
cp -R skills/meshy-3d-generation .claude/skills/

# 3D Printing (optional)
cp -R skills/meshy-3d-printing .claude/skills/

mkdir -p .agents/skills

# Core (required)
cp -R skills/meshy-3d-generation .agents/skills/

# 3D Printing (optional)
cp -R skills/meshy-3d-printing .agents/skills/

Skill vs MCP Server

Both approaches provide the same Meshy API capabilities. Choose based on your preference and setup.

Security & Data

These skills run entirely on your machine and talk to a single service — the Meshy API. No telemetry, no third-party endpoints.

Your API key

• Read from the current session environment, or from .env / .env.local in the current working directory. Home directories and shell profiles are never scanned.
• Sent only in the HTTP Authorization: Bearer header to https://api.meshy.ai. It is never logged in full — scripts print at most a msy_1234... prefix.
• Never persisted by the scripts. The key is written to .env in the current working directory only when you explicitly ask, and that .env is added to .gitignore automatically. It is never written to shell profiles, Windows user variables, or any path outside the working directory. Persisting it globally is offered to you as instructions to run yourself — the skill never does it silently.
• System proxies are bypassed (requests session trust_env = False), so the key is never handed to an environment-configured proxy.

What leaves your machine

• Only what a generation request needs: your API key, text prompts, and image URLs/data (for image-to-3D) — all to api.meshy.ai.
• Generated assets are downloaded and saved locally under ./meshy_output/; nothing else is uploaded.

Filesystem footprint

• Reads: .env / .env.local in the working directory, and any input files you explicitly pass (e.g. local images), at the exact path you provide.
• Writes: ./meshy_output/ (models, thumbnails, metadata.json, history.json) and — on request — .env in the working directory.
• The 3D-printing skill additionally launches an already-installed slicer with your model file; it never downloads or installs software.

For Maintainers

Single sources of truth — edit these, never the generated copies:

After editing a source, regenerate and verify:

python3 scripts/build.py          # regenerate all targets
python3 scripts/build.py --check  # CI mode: fail if outputs are stale, a SKILL.md exceeds 300 lines, or a references/*.md is unlinked

Generated files carry a GENERATED marker comment. CI runs python3 scripts/build.py --check to reject edits that bypass the sources.

License

MIT