How to Use the Contractor+ MCP in OpenAI Agents SDK

Build production-ready, guardrailed agents that manage Contractor+ estimates and field jobs directly through the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Contractor+ MCP to OpenAI Agents SDK

Create your Vinkius account to connect Contractor+ 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 Contractor+ with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guardrailed estimates via OpenAI Agents SDK

Your production agent can draft and inspect quotes without making wild mistakes. By exposing `create_estimate` and `list_estimates` via this MCP Server directly to your OpenAI agent, you let the model build pricing sheets based on real historical data. The built-in safety constraints in this Python SDK mean you can block the agent from sending a broken quote to a client before a human reviews it. You don't have to write custom validation loops for every field. The SDK auto-discovers these tools, allowing your specialized pricing agent to hand off the task to a billing agent once the client approves. It keeps your field operations tidy and stops hallucinated numbers from reaching your customers.

Auto-dispatch field crews and register leads

When a new lead hits your system, your OpenAI agent immediately spins up a profile. The agent invokes `create_client` and `list_service_requests` to categorize the incoming ticket. Because the SDK supports multi-agent handoffs, a triage agent can identify the problem and pass the details to a scheduling agent instantly. You see the entire execution path inside your OpenAI dashboard. If an agent tries to assign a job to a non-existent property, the trace shows you exactly where the logic failed. This makes debugging field dispatch issues painless.

Monitor work orders using this MCP Server

Keep your field teams moving by letting your agent track active progress. The model reads live field updates through `list_work_orders` and `list_jobs` to answer quick status questions from your managers. It pulls the exact job state directly from your Contractor+ account without lag. No more manual status checks in three different apps. You configure the server as an HTTP streamable resource, and your agent treats the field tools as local functions. It gives your back-office team an instant, accurate picture of what's happening on the ground.

Setup guide

Set up Contractor+ 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 Contractor+ tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK with pip, then initialize the connection using MCPServerStreamableHttp. Pass the server URL to the Agent constructor under the mcp_servers parameter, and the agent auto-discovers tools like list_clients instantly.

Yes, you enforce this using the SDK's built-in guardrails. You can limit the agent's tools to read-only operations like list_estimates or intercept write actions like create_estimate for manual approval before they execute.

You define specialized agents, like a billing agent and a dispatch agent. The dispatch agent uses list_work_orders to check jobs, then hands off to the billing agent, who runs list_invoices to settle the account.

Setting this option to true stops the SDK from querying the MCP server for available tools on every single run. It speeds up execution times for tools like list_properties and lowers latency for your live agents.

All client details and estimate values are protected inside an ephemeral, zero-trust V8 sandbox on Vinkius. Your API tokens are managed securely, meaning raw credentials never touch the LLM or your local environment.

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