How to Use the BIMobject MCP in OpenAI Agents SDK

Q: How do I connect BIMobject to my OpenAI Agents SDK project?

Instantiate MCPServerStreamableHttp pointing to your Vinkius MCP Server endpoint. Pass this instance inside the mcpservers list when initializing your agent, and the tools will auto-discover instantly.

Q: Does the BIMobject integration support OpenAI Agents SDK guardrails?

It does. You can intercept tool calls like getproductfiles to validate user permissions before the SDK executes the download action.

Q: How do I filter product queries by specific architectural categories?

Have your agent call listcategories first to get the correct ID. After that, pass that category ID directly into the searchproducts tool query.

Q: How is my BIMobject user profile data kept secure on Vinkius?

Every call to getme runs through an ephemeral, zero-trust V8 sandbox. Vinkius never stores your credentials, and your active session data vanishes the moment the container spins down.

Build production-grade OpenAI Agents SDK workflows that pull real building products and technical files directly from BIMobject.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BIMobject MCP to OpenAI Agents SDK

Create your Vinkius account to connect BIMobject to OpenAI Agents SDK 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 BIMobject with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search BIMobject specs directly inside OpenAI Agents SDK

Your agent can query the entire marketplace using `search_products` to find specific building materials. It parses technical specifications on the fly, matching project constraints against real manufacturer dimensions and performance data. You don't have to write custom scrapers or API connectors anymore. The agent calls `list_categories` and `list_classifications` to drill down into exact architectural divisions before pulling details.

Verify manufacturer details with this MCP Server

When specifying materials for a build, your agent needs to know who makes them. By executing `list_brands` and `get_brand_details`, the agent pulls verified manufacturer info to ensure supply chain compliance. This stops your agent from guessing or hallucinating brand names. It gets clean, structured JSON directly from the source, letting you run automated supplier checks inside your production pipeline.

Pull technical design files on demand

Architectural agents need CAD and Revit files to do their job. This server exposes `get_product_files` and `get_product_details` to feed download URLs straight into your agent's context. Because Vinkius runs this MCP Server in a secure sandbox, your agent gets safe, direct access to files. You don't have to manage session states or storage endpoints on your own server.

Setup guide

Set up BIMobject MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all BIMobject tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives BIMobject tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate BIMobject tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="BIMobject Agent",
            instructions="You have access to BIMobject tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 BIMobject. 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 BIMobject 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 BIMobject MCP in OpenAI Agents SDK

Instantiate `MCPServerStreamableHttp` pointing to your Vinkius MCP Server endpoint. Pass this instance inside the `mcp_servers` list when initializing your agent, and the tools will auto-discover instantly.

It handles heavy traffic easily. Vinkius runs the server in isolated sandboxes, meaning your production pipelines stay fast and isolated from other processes.

It does. You can intercept tool calls like `get_product_files` to validate user permissions before the SDK executes the download action.

Have your agent call `list_categories` first to get the correct ID. After that, pass that category ID directly into the `search_products` tool query.

Every call to `get_me` runs through an ephemeral, zero-trust V8 sandbox. Vinkius never stores your credentials, and your active session data vanishes the moment the container spins down.

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