meshy
Generates 3D models, textures, rigs, animations, and 3D-print files from Meshy AI, plus image generation and task management tools.
README
Meshy 3D — Claude Code plugin
Generate 3D models, textures, rigs, animations, and 3D-print files from any Claude Code session via the Meshy AI API.
Install
-
Get an API key at meshy.ai/settings/api and export it (shell profile):
export MESHY_API_KEY=msy_... -
Add the marketplace and install (restart Claude Code first if you just set the env var):
/plugin marketplace add shoyu-ramen/meshy-claude-plugin /plugin install meshy@meshy-marketplaceFrom a local clone instead:
/plugin marketplace add /path/to/meshy-claude-plugin
What you get
18 MCP tools (mcp__plugin_meshy_meshy__*):
| Group | Tools |
|---|---|
| Generate 3D | text_to_3d (preview→refine), image_to_3d, multi_image_to_3d |
| Process | process_model (remesh/convert/resize/uv_unwrap), retexture |
| Characters | rig, animate, search_animations (~680-action catalog) |
| Images | text_to_image, image_to_image |
| 3D printing | printing (analyze/repair/multi_color) |
| Creative Lab | creative_lab (keychain, fridge-magnet, figure, vinyl-figure, brick-figure, lamp, keycap) |
| Tasks | get_task, list_tasks, delete_task, wait_for_task |
| Utility | download_assets, get_balance |
Slash commands: /meshy:generate "<prompt>" (full pipeline incl. download), /meshy:balance.
Skill: workflow guidance (two-stage text-to-3D, character rig+animate pipeline, credit costs, 3-day URL expiry) loads automatically when relevant.
Usage notes
- All generations are async tasks: create →
wait_for_task→download_assets. Output URLs expire ~3 days after completion — download promptly. analyze-printabilityandsearch_animationsare free;get_balanceshows remaining credits.- Task summaries omit signed URLs to keep agent context small;
raw: truereturns full objects.
Development
npm install
npm run build # bundle src/ → dist/index.mjs (committed — plugins run no install step)
npm run typecheck
npm test
node scripts/stdio-check.mjs # handshake + tools/list
node scripts/stdio-check.mjs --call get_balance '{}'
npm run inspect # MCP inspector UI
src/registry.ts maps every task_type to its API path — generic task tools and download_assets work across all 29 task types from that single table.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.