Compatible with every major AI agent and IDE
What is the Meshy (3D AI) MCP Server?
Connect Meshy to your AI agent to bridge the gap between 2D concepts and 3D reality. This server allows you to generate, refine, and optimize professional-grade 3D meshes using industry-leading AI models.
What you can do
- Text to 3D Generation — Create 3D previews from simple text prompts and refine them into fully textured models with PBR maps.
- Image to 3D Conversion — Turn single or multiple reference images (up to 4 angles) into detailed 3D objects automatically.
- Advanced Retexturing — Apply entirely new styles to existing 3D models using text or image guidance while maintaining geometry.
- Mesh Optimization — Use the remeshing tools to adjust topology (triangles or quads) and target specific polycounts for games or web apps.
- Asset Management — List, retrieve, and manage your generation tasks and 3D assets through a unified interface.
How it works
- Subscribe to this server
- Enter your Meshy API Key
- Start creating 3D assets in Claude, Cursor, or any MCP-compatible client
Who is this for?
- Game Developers — Generate base meshes and textures directly within your development environment to speed up prototyping.
- 3D Artists — Automate the tedious parts of the workflow like initial block-outs, UV mapping, and base texturing.
- Creative Agencies — Rapidly visualize 3D concepts for clients starting from just a text description or a sketch.
Built-in capabilities (17)
Analyze 3D Printability
Create an Animation task
Create an Image to 3D task
Create Image to Image task
Create Multi-Color Print
Create a Multi-Image to 3D task
Create a Remesh task
Create a Retexture task
Create a Rigging task
This is the first step in the Text to 3D workflow. Create a Text to 3D preview task
This is the second step in the Text to 3D workflow. Create a Text to 3D refine task
Create Text to Image task
Delete a Text to 3D task
Get account balance
Get a Text to 3D task by ID
List Text to 3D tasks
Repair 3D Printability
Why Google ADK?
Google ADK natively supports Meshy (3D AI) as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 17 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.
- —
Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution
- —
Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Meshy (3D AI)
- —
Production-ready features like session management, evaluation, and deployment come built-in. not bolted on
- —
Seamless integration with Google Cloud services means you can combine Meshy (3D AI) tools with BigQuery, Vertex AI, and Cloud Functions
Meshy (3D AI) in Google ADK
Meshy (3D AI) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Meshy (3D AI) to Google ADK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Meshy (3D AI) in Google ADK
The Meshy (3D AI) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 17 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Google ADK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Meshy (3D AI) for Google ADK
Every tool call from Google ADK to the Meshy (3D AI) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I add high-quality textures to a 3D model I just generated from text?
After creating a preview with create_text_to_3d_preview, use the create_text_to_3d_refine tool with the resulting task ID. You can enable PBR and HD textures to get professional results.
Can I use multiple photos of an object to create a better 3D model?
Yes! Use the create_multi_image_to_3d tool and provide an array of up to 4 image URLs showing different angles of the object for much higher accuracy.
Is it possible to reduce the polygon count for game engine optimization?
Absolutely. Use the create_remesh tool on any existing model ID. You can specify the target_polycount and choose between triangle or quad topology.
How does Google ADK connect to MCP servers?
Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.
Can ADK agents use multiple MCP servers?
Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.
Which Gemini models work best with MCP tools?
Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.
McpToolset not found
Update: pip install --upgrade google-adk
Explore More MCP Servers
View all →
Xata (Serverless DB)
30 toolsManage your serverless databases via Xata — list organizations, manage projects, branches, and execute SQL queries directly from any AI agent.

Confluent
7 toolsEnable your AI agent to manage Kafka clusters, topics, and environments via the Confluent Cloud API.

ToolJet
4 toolsManage ToolJet databases and trigger workflows directly from your AI agent—query tables, insert data, and automate processes.

Gong
12 toolsUnlock revenue intelligence by analyzing calls, transcripts, and customer interactions.
