How to Use the kvCORE MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK update kvCORE leads?

Yes. Your agent uses the updateleadinfo tool to push JSON strings containing new phone numbers or statuses. It requires zero manual data entry.

Q: Does kvCORE work with OpenAI handoffs?

Absolutely. One agent can run getleaddetails and pass the context to a second agent. The second agent then executes createleadnote based on that exact data.

Connect kvCORE to the OpenAI Agents SDK to build production real estate agents with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect kvCORE MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover kvCORE MCP Server tools

The `search_kvcore_leads` tool returns lead IDs and basic contact info directly to your agent. You pass the server to the `mcp_servers` array and set `cacheToolsList=True` to cut down discovery overhead. Your agent now has immediate read access to the CRM database without writing custom integration logic. Once the agent identifies a target, it calls `update_lead_info` to modify statuses or phone numbers via JSON payloads. The OpenAI dashboard traces every single API call. If a specialized qualification agent needs to hand off a hot lead to a closing agent, the context travels with it.

Audit agent workflows autonomously

The `list_agent_tasks` tool pulls pending follow-ups and daily requirements for any agent profile. Your OpenAI agent reads this queue and cross-references it against `list_lead_activity` to see who actually responded to outreach. You get a factual look at what your team is doing. If an agent misses a step, your system can step in. It triggers `create_lead_note` to document the gap in the lead's profile. You enforce operational standards through code, catching neglected contacts before they go cold.

Pull active property data

The `list_property_listings` tool grabs your active inventory straight from the source. When a buyer asks about available homes, your agent queries this endpoint and formats the response. You don't need a separate MLS feed to answer basic inventory questions. For specific properties, the `get_listing_details` tool fetches the exact metadata. Your agent reads the price, square footage, and status. It uses built-in guardrails to ensure it never quotes an outdated price to a client.

Setup guide

Set up kvCORE 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 kvCORE tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to your agent constructor.

Yes. Your agent uses the update_lead_info tool to push JSON strings containing new phone numbers or statuses. It requires zero manual data entry.

Absolutely. One agent can run get_lead_details and pass the context to a second agent. The second agent then executes create_lead_note based on that exact data.

The OpenAI dashboard logs the error. You trace exactly which tool failed and why, whether it was a bad JSON payload or a timeout.

The MCP Server processes names, phone numbers, and property addresses inside a V8 Isolate Sandbox. Vinkius destroys the environment the second the execution finishes. Your endpoint token is the only auth mechanism, keeping your core credentials off the wire.

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