Can my AI generate a 3D model from a product photo with PBR textures?

Yes! Use the `generate_pbr_textures_3d` tool with your product image URL. Pixazo will generate a 3D model with complete PBR texture maps including albedo, normal, roughness, metallic, and ambient occlusion. You can specify texture resolution (1024, 2048, or 4096) and output format (GLB, OBJ, FBX). The resulting model is ready for game engines, product visualization, and e-commerce platforms with physically accurate materials.

Which model should I use for the highest quality 3D generation?

For the highest quality, use `generate_hunyuan_3d` (Hunyuan by Tencent) or `generate_hyper_3d` (Hyper3D). Both produce production-quality geometry with detailed surface reproduction. Hunyuan excels at accurate proportions and realistic details, while Hyper3D focuses on clean topology and precise texture mapping. For text-to-3D with quality control, use `generate_text_to_3d` with quality set to ultra. All models support output formats GLB, OBJ, FBX, GLTF, and USDZ.

Can I generate 3D characters with automatic rigging for animation?

Yes! Use the `generate_rigged_3d` tool with a character reference image. You can specify the rig type (humanoid, quadruped, or biped) and the API will generate a 3D model with automatic skeletal rigging including bone hierarchies and weight painting. The output is suitable for direct import into Unity, Unreal Engine, Blender, or any animation software. Output formats include FBX (recommended for rigs), GLB, and GLTF.

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

Name: Pixazo 3D
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 Pixazo 3D 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="pixazo_3d_agent",
    instruction=(
        "You help users interact with Pixazo 3D "
        "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 Pixazo 3D MCP Server

Connect your Pixazo 3D API to any AI agent and take full control of production-quality 3D asset generation from images and text through natural conversation.

Google ADK natively supports Pixazo 3D 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

Hunyuan 3D — Generate high-fidelity 3D models from images with Tencent Hunyuan technology
Hyper3D — Create detailed 3D models with high-fidelity geometry and texture reproduction
Tripo3D — Fast 3D generation optimized for speed and quick previews
Trellis3D — Generate structured 3D models with clean topology for editing and animation
Text to 3D — Create 3D models directly from text descriptions with style control
Image to 3D — Convert any image to a 3D model with the optimized Pixazo pipeline
Styled 3D — Generate 3D models in specific artistic styles (photorealistic, anime, cartoon, low-poly)
Low-Poly 3D — Create optimized low-poly models for real-time games and mobile applications
Rigged 3D — Generate 3D characters with automatic skeletal rigging for animation
PBR Textures — Generate 3D models with full PBR texture maps (albedo, normal, roughness, metallic, AO)
Format Conversion — Convert 3D models between GLB, OBJ, FBX, GLTF, USDZ, 3DS, and DAE formats
Mesh Optimization — Optimize 3D meshes for performance and file size reduction

The Pixazo 3D 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 Pixazo 3D to Google ADK via MCP

Follow these steps to integrate the Pixazo 3D 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 Pixazo 3D via MCP

Why Use Google ADK with the Pixazo 3D MCP Server

Google ADK provides unique advantages when paired with Pixazo 3D 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 Pixazo 3D

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

Pixazo 3D + Google ADK Use Cases

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

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

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

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

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

Pixazo 3D MCP Tools for Google ADK (12)

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

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 USDZ for AR", or need 3D format conversion for specific platform or software requirements. Convert 3D models between different file formats

generate_hunyuan_3d

Hunyuan excels at producing detailed geometry with accurate proportions and realistic textures from single or multiple reference images. Accepts image URLs or base64 image data. Returns 3D model files with PBR textures in formats like GLB, OBJ, or FBX. Essential for product visualization, character creation, and asset generation requiring high geometric accuracy. AI agents should use this when users need production-quality 3D models from product photos, concept art, or reference images with precise detail reproduction. Generate 3D models using Hunyuan 3D model from images

generate_hyper_3d

Hyper3D produces clean mesh topology with accurate surface details, making it ideal for game assets, AR/VR content, and e-commerce product displays. Accepts image URLs and returns downloadable 3D files. Essential for applications requiring precise geometry and professional-grade output quality. AI agents should reference this when users need high-detail 3D models suitable for game engines, product showcases, or professional 3D workflows. Generate detailed 3D models using Hyper3D model

generate_image_to_3d

Accepts product photos, concept art, sketches, or any reference image and generates a corresponding 3D model. Supports multiple output formats and quality settings. 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 Pixazo image-to-3D pipeline

generate_lowpoly_3d

Low-poly models use minimal polygons while maintaining recognizable shape, making them ideal for performance-critical applications. Accepts reference images and returns optimized meshes with controlled polygon counts. Essential for game development, mobile applications, web-based 3D viewers, and any scenario requiring efficient 3D rendering. AI agents should reference this when users need low-poly game assets, mobile-optimized 3D models, or performance-friendly 3D content. Generate low-poly 3D models optimized for real-time applications

generate_pbr_textures_3d

PBR textures ensure realistic material appearance under any lighting condition in game engines and 3D renderers. Accepts reference images and returns 3D models with texture map sets. Essential for game asset creation, product visualization requiring realistic materials, and applications needing physically accurate rendering. AI agents should reference this when users need game-ready assets with full PBR materials, product visualizations with realistic surface appearance, or models with complete texture map sets. Generate 3D models with full PBR texture maps (albedo, normal, roughness, metallic, AO)

generate_rigged_3d

Supports character models, creatures, and articulated objects. The generated rigs include bone hierarchies and weight painting suitable for standard animation workflows. Accepts character reference images and returns rigged 3D files. Essential for game character creation, animated content pipelines, and applications requiring animation-ready 3D assets. AI agents should use this when users ask "create an animated-ready 3D character", "generate a rigged model from this character image", or need animation-ready 3D output. Generate 3D models with automatic skeletal rigging for animation

generate_styled_3d

Users provide a reference image and select the desired output style. Essential for stylized game assets, anime character creation, cartoon visualization, and artistic 3D content. AI agents should use this when users ask "create an anime-style 3D character from this image", "generate a cartoon 3D model", or need stylized 3D output matching specific artistic direction. Generate 3D models with specific artistic styles

generate_text_to_3d

Users describe the desired 3D object in natural language and receive a generated model. Supports style modifiers, polygon count preferences, and format selection. 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

generate_trellis_3d

Trellis3D excels at creating models with well-distributed polygons and logical edge flow. Accepts image URLs and returns clean 3D meshes. Essential for character rigging preparation, animation-ready assets, and applications requiring well-organized mesh structure. AI agents should reference this when users need edit-friendly 3D models, animation-ready meshes, or assets with clean topology for downstream processing. Generate structured 3D models using Trellis3D with clean topology

generate_tripo_3d

Tripo3D is ideal for rapid prototyping, batch processing, and applications where generation time is important. Accepts image URLs and returns 3D models with reasonable geometry and textures. Essential for quick 3D previews, iterative design workflows, and content pipelines requiring fast turnaround. AI agents should use this when users need fast 3D generation, quick previews, or batch processing of multiple images. Generate 3D models using Tripo3D for fast generation

optimize_3d_mesh

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 meshes for performance and file size reduction

Example Prompts for Pixazo 3D in Google ADK

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

"Generate a 3D model of a running shoe from this product image: https://example.com/shoe.jpg"

"Create a low-poly 3D tree for my mobile game from this reference image."

"Generate an anime-style 3D character from this concept art."

Troubleshooting Pixazo 3D MCP Server with Google ADK

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

McpToolset not found

Update: pip install --upgrade google-adk

Pixazo 3D + Google ADK FAQ

Common questions about integrating Pixazo 3D 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.