Can my AI generate a 3D model from a text description with specific style?

Yes! Use the `generate_text_to_3d` tool with your text prompt and style parameter. Choose from models like Hunyuan 3D Pro (highest quality), TRELLIS.2-4B (structured topology), or Tripo (fastest generation). Specify style as photorealistic, stylized, anime, cartoon, or lowpoly. Set face limits and density presets. Output in GLB, OBJ, FBX, STL, PLY, USDZ, or 3MF formats.

How do I apply AI texturing to an existing 3D model?

Use the `generate_ai_texturing` tool with your existing 3D model URL. Provide a text prompt describing the desired material (e.g., rusty metal, polished wood, cartoon stone) or a style image URL for texture transfer. The API generates complete PBR texture sets including albedo, normal, metallic, and roughness maps. You can specify texture resolution from 1024 to 4096 pixels.

Can I repair and prepare a 3D model for 3D printing?

Yes! Use `repair_3d_mesh` to fix non-manifold geometry, holes, and inverted normals making your model watertight for 3D printing. Then use `calculate_volume_3d` to get volume, surface area, and weight estimates for your chosen material (PLA, ABS, resin, metal). Finally use `convert_3d_format` to output in STL or 3MF format which are optimal for 3D printing slicers.

3D AI Studio MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: 3D AI Studio
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add 3D AI Studio as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="3d_ai_studio_agent",
    instruction=(
        "You help users interact with 3D AI Studio "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About 3D AI Studio MCP Server

Connect your 3D AI Studio API to any AI agent and take full control of production-quality 3D generation, AI texturing, mesh processing, and rendering through natural conversation.

Google ADK natively supports 3D AI Studio as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Text to 3D — Generate 3D models from text prompts using Hunyuan 3D, TRELLIS.2, and Tripo models
Image to 3D — Convert any image to a 3D model with multiple AI model options
Multi-View to 3D — Generate accurate 3D models from multiple reference images
AI Texturing — Apply AI-powered PBR texturing to existing models using text or image prompts
Remeshing — Optimize topology with tri or quad mesh remeshing
Mesh Repair — Fix non-manifold geometry, holes, and inverted normals
Format Conversion — Convert between GLB, OBJ, FBX, STL, PLY, USDZ, and 3MF formats
Model Optimization — Reduce polygon count and compress for web and mobile
3D Rendering — Generate high-quality images and turntable videos up to 4K
Mesh Segmentation — Automatically segment 3D mesh parts by semantic components
Texture Baking — Bake high-poly details onto low-poly game-ready meshes
Volume Calculator — Calculate volume, surface area, and weight estimates for 3D printing

The 3D AI Studio MCP Server exposes 12 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect 3D AI Studio to Google ADK via MCP

Follow these steps to integrate the 3D AI Studio MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from 3D AI Studio via MCP

Why Use Google ADK with the 3D AI Studio MCP Server

Google ADK provides unique advantages when paired with 3D AI Studio through the Model Context Protocol.

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 3D AI Studio

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 3D AI Studio tools with BigQuery, Vertex AI, and Cloud Functions

3D AI Studio + Google ADK Use Cases

Practical scenarios where Google ADK combined with the 3D AI Studio MCP Server delivers measurable value.

Enterprise data agents: ADK agents query 3D AI Studio and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine 3D AI Studio tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query 3D AI Studio regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including 3D AI Studio

3D AI Studio MCP Tools for Google ADK (12)

These 12 tools become available when you connect 3D AI Studio to Google ADK via MCP:

bake_textures_3d

Supports baking normal maps, ambient occlusion, curvature, and other detail maps. Essential for game asset pipelines where high-detail sculpted models need to be baked onto game-ready low-poly meshes. Returns optimized models with baked texture maps. AI agents should use this when users ask "bake normal maps from high-poly to low-poly", "bake ambient occlusion for this model", or need texture baking for game asset preparation. Bake texture maps onto 3D models for optimized rendering

calculate_volume_3d

Supports unit specification (mm, cm, inches, meters) and material density for weight estimation. Essential for 3D printing cost estimation, material requirements planning, shipping calculations, and physical property analysis of 3D models. Returns detailed measurement data. AI agents should reference this when users ask "calculate the volume of this 3D model", "estimate weight for PLA printing", or need physical measurements for manufacturing or cost planning. Calculate volume and physical measurements of 3D models

convert_3d_format

Preserves geometry, textures, materials, and rigging data during conversion. Essential for pipeline integration, platform compatibility, and format standardization. AI agents should use this when users ask "convert this GLB model to FBX", "change this 3D file to STL for 3D printing", or need 3D format conversion for specific platform or software requirements. Convert 3D models between different file formats

generate_ai_texturing

Can repaint or restyle existing 3D models with new materials, colors, and surface details. Generates complete PBR texture sets (albedo, normal, metallic, roughness) from descriptions like "rusty metal", "polished wood", or "cartoon stone". Essential for material iteration, style transfers on 3D assets, and adding surface details to generated models. AI agents should reference this when users ask "add rusty metal texture to this model", "restyle this character with cartoon textures", or need AI-powered material generation on existing 3D meshes. Apply AI-powered PBR texturing to existing 3D models using text or image prompts

generate_image_to_3d

2-4B, and Tripo variants. Accepts product photos, concept art, sketches, or any reference image and generates a corresponding 3D model with PBR textures. Supports style modifiers, face limits, density presets, and orientation control. Returns 3D model files in multiple formats. Essential for e-commerce product visualization, concept art to 3D conversion, and general image-to-3D workflows. AI agents should reference this when users ask "convert this product photo to 3D", "turn this sketch into a 3D model", or need reliable general-purpose image-to-3D conversion. Convert images to 3D models using AI-powered image-to-3D pipeline

generate_multiview_to_3d

Users provide 2 or more images from different angles and the AI constructs a more accurate 3D representation. Essential for product visualization requiring precise geometry, architectural elements, and objects that need to match reference from multiple viewpoints. Supports all available models and output formats. AI agents should use this when users ask "create a 3D model from these multiple product photos", "generate accurate 3D from front and side views", or need multi-view 3D reconstruction. Generate 3D models from multiple reference images for higher accuracy

generate_text_to_3d

2-4B, and Tripo (v3.0, v3.1, P1). Users describe the desired 3D object in natural language and receive a generated model with optional style control, face limits, and density presets (high/medium/low). Returns 3D model files in GLB format by default with PBR textures. Supports output formats GLB, OBJ, FBX, STL, PLY, USDZ, and 3MF. Essential for concept exploration, rapid prototyping from descriptions, and applications where users describe rather than show what they want. AI agents should use this when users ask "create a 3D model of a fantasy sword", "generate a 3D tree from text", or need text-driven 3D generation. Generate 3D models directly from text descriptions

optimize_3d_model

Accepts existing 3D model URLs and returns optimized versions with controlled quality settings. Essential for web-based 3D applications, mobile optimization, file size reduction, and performance-critical 3D rendering. AI agents should reference this when users ask "optimize this 3D model for web", "reduce polygon count of this model", or need mesh optimization for performance or file size constraints. Optimize 3D models for performance and file size reduction

remesh_3d_model

Accepts existing 3D model URLs and returns remeshed versions with controlled face counts and topology type (tri or quad). Essential for game asset preparation, animation-ready meshes, and applications requiring clean topology. AI agents should use this when users ask "remesh this model with clean quads", "optimize topology for animation", or need topology conversion on existing 3D assets. Remesh 3D models with optimized tri or quad topology

render_3d_model

Supports turntable animations, hero shots, and product visualization renders. Outputs images up to 4K resolution in PNG or JPG format. Essential for product showcases, portfolio presentations, marketing materials, and social media content from 3D assets. AI agents should use this when users ask "render this model from multiple angles", "create a turntable video of this 3D model", or need marketing-quality renders from 3D files. Generate rendered images or videos from 3D models

repair_3d_mesh

Accepts existing 3D model URLs and returns repaired, watertight meshes suitable for 3D printing, game engines, and further processing. Essential for 3D printing preparation, fixing generated model artifacts, and ensuring mesh integrity. AI agents should reference this when users ask "fix this mesh for 3D printing", "repair non-manifold geometry", or need mesh cleanup before further processing. Repair 3D mesh issues including non-manifold geometry, holes, and inverted normals

segment_3d_mesh

g., head, body, arms, legs for characters; wheels, body, windows for vehicles). Essential for rigging preparation, material assignment per part, and game engine component workflows. Returns segmented mesh with labeled parts. AI agents should reference this when users ask "segment this character mesh into body parts", "identify components of this vehicle model", or need automatic mesh part identification for further processing. Apply semantic segmentation to 3D mesh parts

Example Prompts for 3D AI Studio in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with 3D AI Studio immediately.

"Generate a 3D model of a medieval castle from text description."

"Apply rusty metal texture to this 3D model: https://example.com/car.glb"

"Repair this mesh for 3D printing and calculate the volume in PLA material."

Troubleshooting 3D AI Studio MCP Server with Google ADK

Common issues when connecting 3D AI Studio to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

3D AI Studio + Google ADK FAQ

Common questions about integrating 3D AI Studio MCP Server with Google ADK.

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.