How to Use the Constructor MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK handle Constructor pagination safely?

Yes, the agent uses searchpagination to verify gateway history before requesting the next page. This prevents the agent from making infinite loops or hitting empty pages during large catalog searches.

Q: How does the OpenAI Agents SDK cache Constructor tool lists?

You set cacheToolsList=True inside the server configuration parameters. This prevents the SDK from querying the Vinkius endpoint for tool definitions on every single message exchange, keeping latency low.

Q: How do agents handle brand plan math during searches?

The agent invokes browsebrand to inspect internal arrays. This lets the model resolve pricing tiers and customer-specific plan limits before presenting products.

Run production-grade e-commerce search agents with OpenAI Agents SDK using safe Constructor routing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Constructor MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure e-commerce queries with OpenAI Agents SDK

This integration uses `search_products` to pull CRM records from Constructor.io into your OpenAI agent pipeline. It handles the extraction automatically, validating each step through the SDK guardrails before hitting your live inventory. Instead of risking broken search flows, the MCP Server uses `search_pagination` to verify gateway history. If a query fails validation, the SDK handoff mechanism routes the task to a recovery agent before any bad payload reaches your users.

Track personalized recommendations in your dashboard

Tracking recommendation pipelines requires calling `get_recommendations` to inspect cloud logs for vault limits. You can monitor these calls directly inside your OpenAI tracing dashboard to catch performance issues early. Here is the thing: debugging recommendation pipelines shouldn't feel like guesswork. When the agent uses `browse_brand` to resolve plan math, every step is logged directly in your OpenAI run history, making it easy to spot broken rules.

Validate account logic inside active agent runs

Your agent invokes `autocomplete` to pull active account logic directly into its system prompt. This keeps the model aligned with your business rules without requiring hardcoded instructions. Because the OpenAI SDK caches these tool definitions with `cacheToolsList=True`, you don't pay a latency penalty on every turn. The agent pulls active hold parsing via `custom_search` and immediately knows which filters to apply without making redundant network hops.

Setup guide

Set up Constructor 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 Constructor tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Constructor 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="Constructor Agent",
            instructions="You have access to Constructor 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 Constructor. 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 Constructor 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 Constructor MCP in OpenAI Agents SDK

Install the SDK and pass the Vinkius HTTP endpoint to your MCPServerStreamableHttp config. You then feed this server instance directly into the `mcp_servers` list when initializing your agent.

Yes, the agent uses `search_pagination` to verify gateway history before requesting the next page. This prevents the agent from making infinite loops or hitting empty pages during large catalog searches.

You set `cacheToolsList=True` inside the server configuration parameters. This prevents the SDK from querying the Vinkius endpoint for tool definitions on every single message exchange, keeping latency low.

The agent invokes `browse_brand` to inspect internal arrays. This lets the model resolve pricing tiers and customer-specific plan limits before presenting products.

All traffic routes through ephemeral V8 isolates on Vinkius, meaning no search queries or customer CRM records are stored. The server acts as a zero-trust pass-through, disposing of the execution context the millisecond the tool execution finishes.

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