How to Use the Nestoria MCP in OpenAI Agents SDK

Q: Can I limit which property tools my OpenAI Agents SDK agent can access?

Since Nestoria only exposes the searchlistings tool, your agent only gets access to search functions. There are no write operations or booking tools, meaning your agent cannot accidentally make unauthorized modifications.

Q: Does the Nestoria search handle both buy and rent options in OpenAI Agents SDK?

Yes. The searchlistings tool accepts a listing type parameter. Your OpenAI Agents SDK client can dynamically switch between rental and purchase markets based on user intent.

Q: How does caching work for Nestoria queries in OpenAI Agents SDK?

Set cacheToolsList=True during your transport initialization. This keeps your OpenAI Agents SDK from repeatedly querying the server for the tool schema, saving valuable milliseconds on every run.

Build production-grade real estate agents that search global properties with the OpenAI Agents SDK and Nestoria.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nestoria MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Safe Property Searches in the OpenAI Agents SDK

Connect your agentic workflows directly to live property markets. This integration exposes the `search_listings` tool, letting your OpenAI Agents SDK system query real estate data on demand without custom API wrappers. The SDK handles agent handoffs automatically while executing searches. You can let a budget specialist agent gather raw pricing data and then hand it off to a local market agent to filter the results.

Validate Real Estate Queries Before Execution

Guardrails inside this MCP Server protect your live systems from bad inputs. When your agent calls `search_listings`, the OpenAI Agents SDK checks the parameters against your schema constraints before hitting the live Nestoria database. This prevents broken queries from wasting your API limits or throwing unhandled exceptions. Your agent gets clean, structured real estate data back every single time, keeping your production pipelines stable.

Trace Every Property Search on Your Dashboard

Debugging real estate agents is notoriously painful when they hallucinate prices. By running this MCP Server, every single call to `search_listings` is logged and traced right inside your OpenAI developer dashboard. You see exactly what parameters the agent passed—like target cities, price caps, or buy versus rent flags. If an agent goes off track during a search, you can pinpoint the bad prompt in seconds.

Setup guide

Set up Nestoria 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 Nestoria tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and spin up the MCP Server streamable HTTP transport. Pass the server instance directly into your Agent constructor using the `mcp_servers` list. Your agents will auto-discover `search_listings` instantly.

Since Nestoria only exposes the `search_listings` tool, your agent only gets access to search functions. There are no write operations or booking tools, meaning your agent cannot accidentally make unauthorized modifications.

Yes. The `search_listings` tool accepts a listing type parameter. Your OpenAI Agents SDK client can dynamically switch between rental and purchase markets based on user intent.

Set `cacheToolsList=True` during your transport initialization. This keeps your OpenAI Agents SDK from repeatedly querying the server for the tool schema, saving valuable milliseconds on every run.

Your location queries and budget limits are processed in ephemeral V8 sandboxes. Vinkius does not store your search parameters, and the Nestoria API only sees the raw, anonymized search criteria.

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