How to Use the JobNimbus MCP in OpenAI Agents SDK

Q: How do I configure tool discovery for JobNimbus in the OpenAI Agents SDK?

Look, here's the deal. You initialize the connection using MCPServerStreamableHttp and pass the server instance directly to the Agent constructor in your Python script. The OpenAI Agents SDK automatically discovers all ten tools, including listjobs and getcontact, with zero manual schema definition. Setting cacheToolsList=True in your Python code will keep your JobNimbus agent response times fast.

Build production-ready OpenAI Agents that safely manage your JobNimbus construction pipeline with built-in execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JobNimbus MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe Construction Pipeline Routing with OpenAI Agents

Your OpenAI Agents can now safely inspect your JobNimbus pipeline using `list_workflows` and `list_boards` without risking unauthorized CRM changes. By combining the OpenAI Agents SDK handoff pattern with these read-only JobNimbus tools, you can build a triage agent that routes construction data to specialized field agents. This setup prevents a single OpenAI Agent from having too much control over your JobNimbus boards, keeping your production deployment secure. The primary OpenAI Agent uses `get_job` to check active JobNimbus project stages before deciding which specialist agent should take over. Because the OpenAI Agents SDK supports full tracing, you can monitor every single JobNimbus tool call directly on your OpenAI developer dashboard. You will see exactly when your OpenAI Agent queried `get_job`, making debugging your JobNimbus construction workflows straightforward.

Automated Job Auditing via OpenAI Agents MCP Server

Keep your field operations aligned by letting your OpenAI Agents run automated background audits using JobNimbus tools like `list_tasks` and `list_jobs`. The OpenAI Agents SDK executes these tasks to match outstanding JobNimbus roof installation duties with active project files. This automated cross-referencing ensures that no JobNimbus task is left orphaned in your OpenAI Agents SDK pipeline. Since you are deploying this to production, you can set strict OpenAI Agents SDK validation guardrails on all incoming JobNimbus data. Before your OpenAI Agent processes any `list_tasks` output, the SDK verifies the parameters to ensure the agent never queries an invalid JobNimbus ID. This prevents your active OpenAI Agents from sending malformed parameters back to your JobNimbus CRM.

Instant Customer Intelligence and Billing Audits

Give your customer-facing OpenAI Agents immediate context by pulling complete JobNimbus customer profiles using `get_contact` and checking financial statuses with `list_payments`. The OpenAI Agents SDK allows your support agent to verify outstanding JobNimbus balances before drafting any follow-up emails. This ensures your OpenAI Agents never pitch new services to a JobNimbus contact with an overdue account. You can restrict these sensitive JobNimbus tool calls to specific financial agents within your OpenAI Agents SDK configuration. By separating concerns in your OpenAI Agents SDK setup, your general customer service agent only searches for names using `list_contacts`, while your billing agent accesses JobNimbus payment histories. This keeps your sensitive JobNimbus financial data protected behind strict code-level boundaries inside your OpenAI Agents SDK setup.

Setup guide

Set up JobNimbus 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 JobNimbus tools at runtime.
3

Create your Agent

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

Run the agent

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

Look, here's the deal. You initialize the connection using `MCPServerStreamableHttp` and pass the server instance directly to the Agent constructor in your Python script. The OpenAI Agents SDK automatically discovers all ten tools, including `list_jobs` and `get_contact`, with zero manual schema definition. Setting `cacheToolsList=True` in your Python code will keep your JobNimbus agent response times fast.

Yes, you can control tool access by creating specialized agents and registering only specific tool definitions with each one. For example, assign `get_job` to your project tracking agent while keeping `list_payments` restricted to your billing agent in your OpenAI Agents SDK setup. This prevents a single agent from accessing parts of your JobNimbus CRM it does not need.

The OpenAI Agents SDK relies on your Python application's async loop to manage execution flow when calling tools over the MCP connection. You can implement custom middleware or backoff logic around the client connection to queue requests before they hit JobNimbus. This keeps your production agents from hitting JobNimbus API limits during high-volume syncs.

You can inspect the complete execution trace directly in your OpenAI developer dashboard. Every time the agent invokes `list_workflows` or `get_contact` via the MCP Server, the input parameters and raw JSON responses are logged. This makes it easy to spot where an OpenAI Agent passed an invalid ID or failed to parse a JobNimbus CRM field.

Your sensitive JobNimbus CRM data, including customer addresses, phone numbers, and payment records, is isolated within a secure V8 sandbox. Vinkius runs this server in an ephemeral container, meaning no credentials or customer histories are ever written to persistent storage. All data transfers occur over encrypted channels directly between your OpenAI python runtime and the JobNimbus API.

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