How to Use the AgentFire MCP in OpenAI Agents SDK

Q: How do I connect the AgentFire MCP Server to the OpenAI Agents SDK?

Install the openai-agents package via pip. Pass the Vinkius endpoint URL into MCPServerStreamableHttp and add it to your Agent constructor's server list.

Q: Can my AgentFire agent update lead statuses in the OpenAI Agents SDK?

Yes. The system exposes the updatelead tool to modify existing records. You only need to pass the specific fields you want to change, leaving the rest of the lead data untouched.

Q: Does the OpenAI Agents SDK cache AgentFire property data?

You can set cacheToolsList=True during setup to speed up initialization. The actual property data fetched from tools like getlisting remains dynamic.

Q: How do I search for specific homes using AgentFire and the OpenAI Agents SDK?

Your agent calls searchlistings with the buyer's parameters. The SDK automatically formats the request and parses the returned properties back into the conversation.

Connect your real estate brokerage data to the OpenAI Agents SDK for automated lead routing and property searches.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AgentFire MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate lead capture with OpenAI Agents SDK

AgentFire acts as an MCP server giving your production agent direct access to your brokerage's lead pipeline. When a new inquiry drops in, your system calls `create_lead` to instantly log the prospect using their required email address. Handing off between specialized agents works perfectly here—one agent qualifies the buyer, while another runs `update_lead` to append specific budget constraints or preferred zip codes. You do not have to write custom API wrappers to manage your contacts. The SDK auto-discovers endpoints like `list_leads` and `get_lead` right out of the box. OpenAI's built-in guardrails ensure your agent formats the email strings correctly before execution, preventing malformed data from hitting your CRM.

Query live property listings

Finding the right home for a client requires real-time data access. Your agent executes `search_listings` to filter available properties based on the buyer's criteria. Once it identifies a match, calling `get_listing` pulls the full property details, including pricing and square footage, directly into the agent's context window. Building a deployed product means relying on accurate inventory. Using `list_listings`, a background process can periodically check the market and trigger alerts for new homes. You can monitor all these tool calls through the OpenAI dashboard tracing to see exactly which properties your agent evaluated.

Verify AgentFire MCP Server status

Keeping a production system running requires constant health checks. The code pings `check_agentfire_status` to confirm API connectivity before attempting to synchronize a massive batch of contacts. If the connection drops, you configure the agent to pause operations rather than throwing unhandled exceptions. Context matters when agents interact with clients on your behalf. Fetching `get_profile` loads your specific brokerage details into the prompt. This ensures the agent accurately represents your brand and contact information while fetching data via `list_contacts`.

Setup guide

Set up AgentFire 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 AgentFire tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the `openai-agents` package via pip. Pass the Vinkius endpoint URL into `MCPServerStreamableHttp` and add it to your Agent constructor's server list.

Yes. The system exposes the `update_lead` tool to modify existing records. You only need to pass the specific fields you want to change, leaving the rest of the lead data untouched.

You can set `cacheToolsList=True` during setup to speed up initialization. The actual property data fetched from tools like `get_listing` remains dynamic.

Your agent calls `search_listings` with the buyer's parameters. The SDK automatically formats the request and parses the returned properties back into the conversation.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. Your client emails, contact lists, and property data pass directly through the endpoint token without being stored. The sandbox destroys itself immediately after the request 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