How to Use the Imagine.io MCP in LlamaIndex

Q: How do I connect the Imagine.io MCP Server to LlamaIndex?

Install the tool spec with pip install llama-index-tools-mcp. Initialize the BasicMCPClient with your Vinkius URL, wrap it in McpToolSpec, and call totoollistasync() to pass the tools to your FunctionAgent.

Q: Can LlamaIndex search through past Imagine.io render runs?

Yes. Your agent can call listrenders to pull historical render data, index those records into your vector store, and search them later to find existing images before starting a new job.

Q: How does the agent check material availability in Imagine.io using LlamaIndex?

The agent executes listmaterials to gather all texture details, indexes them, and performs a semantic search to find the closest match to the user's request before starting the render.

Q: Can I restrict which tools the LlamaIndex agent can access?

Yes, you can use the allowedtools filter when setting up your tool specification to limit the agent to read-only tools like listscenes or write tools like createrenderjob.

Index your Imagine.io 3D catalog data into LlamaIndex vector stores for context-aware rendering.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Imagine.io MCP to LlamaIndex

Create your Vinkius account to connect Imagine.io to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Imagine.io with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index and query your 3D product catalog

The `list_products` tool outputs your complete 3D catalog data so your agent can index it directly into a vector store. This lets you run semantic search queries over your physical inventory details instead of relying on exact keyword matches. By combining this tool with LlamaIndex, you build RAG applications that ground agent decisions in actual live catalog data. The agent fetches product details via `get_product` and retrieves matching historical records instantly.

Track active render status in your knowledge base

The `list_renders` tool retrieves active and completed image assets to update your local search index. Your agent queries this list to match user requests with existing images, preventing duplicate render runs. When a new visual is required, the agent triggers `create_render_job` and monitors it with `get_job_status`. The final asset metadata is then indexed, keeping your searchable knowledge base perfectly aligned with your actual storage.

Retrieve scene specifications via this MCP Server

The `get_scene` tool extracts structural details and camera angles from your stored templates. This MCP Server lets your agent inspect the spatial parameters of a scene before committing to a render. Using `list_scenes` alongside LlamaIndex allows your system to index template names and layouts. Your agent can search these indexes to find the exact room setup that matches a customer's textual description.

Setup guide

Set up Imagine.io MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Imagine.io MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Imagine.io tools.",
)
response = await agent.run("List recent Imagine.io data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Imagine.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Imagine.io now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Imagine.io MCP in LlamaIndex

Install the tool spec with `pip install llama-index-tools-mcp`. Initialize the `BasicMCPClient` with your Vinkius URL, wrap it in `McpToolSpec`, and call `to_tool_list_async()` to pass the tools to your `FunctionAgent`.

Yes. Your agent can call `list_renders` to pull historical render data, index those records into your vector store, and search them later to find existing images before starting a new job.

The agent executes `list_materials` to gather all texture details, indexes them, and performs a semantic search to find the closest match to the user's request before starting the render.

Yes, you can use the `allowed_tools` filter when setting up your tool specification to limit the agent to read-only tools like `list_scenes` or write tools like `create_render_job`.

All communication runs through a zero-trust, ephemeral V8 sandbox managed by Vinkius. Your API keys and render statuses are never stored on the platform, protecting your proprietary asset metadata from unauthorized access.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript