How to Use the NinjaCat MCP in OpenAI Agents SDK

Q: How do I handle multiple advertisers in my NinjaCat account with an OpenAI agent?

Your agent should first use listadvertisers to get the ID for the correct advertiser. Then, it passes that ID to other tools like listreports to get data for that specific account.

Pull NinjaCat reports and campaign data right into your production OpenAI Agents SDK system. No more manual downloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NinjaCat MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Marketing Reports on Autopilot

This toolset gives your agent direct access to your NinjaCat reports. Use `list_reports` to see what's available, then have the agent grab a download link with `get_report_download_url` and send it straight to Slack or a customer. It's a simple, reliable way to automate daily reporting tasks. Because you're using the OpenAI Agents SDK, you can build guardrails around this. For example, you can set a rule that prevents the agent from pulling reports for a specific advertiser, adding a layer of safety before the action is ever executed. Your agent gets autonomy, you keep control.

Monitor Campaigns and Data Sources

Your agent can keep an eye on active campaigns and data connections. It uses `list_agency_campaigns` to get a full campaign list and `list_data_sources` to check what's connected, like your Google or Facebook Ads accounts. This is for monitoring, not management—the tools are read-only. You can build specialized agents. One agent could monitor campaign lists from NinjaCat, and if it spots a new one, it hands off the advertiser ID to another agent responsible for pulling performance reports. The SDK's handoff feature makes these multi-agent workflows possible.

Map Your Account with the OpenAI Agents SDK

Before your agent can act, it needs to understand the landscape. Tools like `list_advertisers` and `get_agency_info` let it build a map of your entire account structure. It can find the exact advertiser ID it needs without you having to look it up manually. Every action your agent takes with this MCP Server is logged in the OpenAI dashboard. You get a full trace of it finding an advertiser, listing its reports, and getting a download URL. This makes debugging dead simple and gives you a clear audit trail.

Setup guide

Set up NinjaCat 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 NinjaCat tools at runtime.
3

Create your Agent

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

Run the agent

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

You provide the Vinkius MCP endpoint URL when you initialize the `MCPServerStreamableHttp` object. The SDK handles tool discovery automatically, so all the NinjaCat tools are immediately available to your agent.

No, this MCP server provides read-only tools. Your agent can list existing reports and download them using `get_report_download_url`, but it can't create or modify reports within NinjaCat.

The biggest advantage is safety and control. The SDK's built-in guardrails let you validate your agent's plan *before* it calls a NinjaCat tool, preventing unwanted actions. This is critical for production systems.

Your agent should first use `list_advertisers` to get the ID for the correct advertiser. Then, it passes that ID to other tools like `list_reports` to get data for that specific account.

The server only accesses the NinjaCat data your agent explicitly requests, like campaign lists and report metadata. Vinkius uses ephemeral, sandboxed environments for each request, and your connection is secured by a single endpoint token. No credentials or report contents are stored.

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