How to Use the CaptivateIQ MCP in OpenAI Agents SDK

Get your OpenAI Agents SDK pipelines talking directly to CaptivateIQ to audit payouts and manage rep compensation plans automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CaptivateIQ MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit commission payouts with OpenAI Agents SDK

This MCP Server exposes tools like `list_commission_payouts` to pull historical compensation records directly into your OpenAI agent runs. By mapping these tools into your agent config, your system checks actual numbers against plan designs without human intervention. You build guardrails to verify that the numbers returned from `list_payout_statements` match your internal database records before pushing updates. The SDK handles the API handoffs, making sure your agent doesn't guess or hallucinate financial numbers.

Pull workbook calculations into agent workflows

The `list_workbooks` tool lets your agent inspect the mathematical foundation of your compensation plans. Instead of manually exporting spreadsheets, your agent queries `list_worksheets` to trace how a specific calculation was built inside CaptivateIQ. This direct access means your autonomous agents can debug calculation logic on the fly using our MCP Server. You get full execution tracing inside your OpenAI dashboard to see exactly when and why an agent inspected a worksheet.

Resolve rep disputes using multi-agent handoffs

This MCP Server connects your dispute-resolution agent to the `list_commission_inquiries` tool to pull active rep complaints. A triage agent reads the inquiry, then hands off the task to a specialized agent equipped with `get_employee_details` to verify the rep's plan. This multi-agent design keeps your system secure by isolating employee-sensitive tools. The agent gets the exact context it needs, updates the status using `get_account_status`, and closes the loop without exposing extra data.

Setup guide

Set up CaptivateIQ 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 CaptivateIQ tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package using pip install openai-agents. Next, create an MCPServerStreamableHttp instance with your Vinkius endpoint URL and pass it directly to your Agent constructor.

You control tool exposure during agent initialization. You can restrict the agent to read-only tools like `list_payout_statements` or `list_employees` to prevent accidental changes.

The SDK relies on your connection settings to manage requests. If your agent runs multiple queries using `list_commission_payouts`, the Vinkius platform manages the rate limiting to keep things running.

Every tool call, whether it's checking account status or pulling employee details, shows up in your OpenAI dashboard. You see the exact input arguments and the raw JSON response returned from the server.

Vinkius runs the MCP server in an isolated V8 sandbox, meaning your raw API keys and employee salary data never touch public LLM servers. Only the specific JSON payloads returned by tools like `get_employee_details` are sent to your OpenAI client over secure HTTPS.

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