How to Use the Evil Insult MCP in OpenAI Agents SDK

Q: How do I use the Evil Insult tool with my OpenAI Agents SDK agent?

First, install the client. Then, create an MCPServerStreamableHttp instance with the server URL Vinkius provides. Pass that server instance into your Agent constructor's mcpservers list, and the tools are discovered automatically.

Q: Can I get a specific type of insult from the Evil Insult API with the OpenAI Agents SDK?

No. The generateinsult tool fetches a random insult. The OpenAI Agents SDK is responsible for securely calling the tool, not for changing what the tool does.

Q: How does caching work for the Evil Insult tool and the OpenAI Agents SDK?

For better performance, set cacheToolsList=True when you configure the server connection. This prevents your agent from re-fetching the tool definition for generateinsult on every startup.

Generate insults in your production application using the OpenAI Agents SDK. With full tracing and guardrails included.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Evil Insult MCP to OpenAI Agents SDK

Create your Vinkius account to connect Evil Insult 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 Evil Insult with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Insults On Demand

This MCP Server gives your agent one tool: `generate_insult`. When you connect it, your OpenAI Agent automatically discovers the tool and knows how to call it. There's no extra configuration to get it working. Your agent can now generate a random, creative insult from the Evil Insult API. You can call it directly or let the agent decide when a situation calls for a bit of snark. It's a simple way to test your agent's ability to use external tools.

Use Guardrails with Your MCP Server

The OpenAI Agents SDK isn't just about calling tools. It provides guardrails to validate what your agent is about to do. Before `generate_insult` is executed, you get a chance to inspect and approve the action. This means you can build a production system without worrying about your agent going rogue. Even with a tool designed for chaos, you stay in control. Every call is logged, so you have a complete audit trail of every insult generated.

Full Observability in Your Dashboard

Every time your agent uses the `generate_insult` tool, the entire operation is traced. You can see the request, the parameters, and the resulting insult right in the OpenAI dashboard. This isn't a black box. You get full visibility into how your agent interacts with this MCP Server. This is essential for debugging and understanding why your agent chose to generate an insult at a particular moment.

Setup guide

Set up Evil Insult 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 Evil Insult tools at runtime.
3

Create your Agent

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

Run the agent

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

First, install the client. Then, create an `MCPServerStreamableHttp` instance with the server URL Vinkius provides. Pass that server instance into your Agent constructor's `mcp_servers` list, and the tools are discovered automatically.

No. The `generate_insult` tool fetches a random insult. The OpenAI Agents SDK is responsible for securely calling the tool, not for changing what the tool does.

It's a great way to test your end-to-end tool usage pipeline. It confirms your agent can connect to an MCP Server, execute a tool, and handle the response, all with the safety and tracing of the OpenAI platform.

For better performance, set `cacheToolsList=True` when you configure the server connection. This prevents your agent from re-fetching the tool definition for `generate_insult` on every startup.

No, it doesn't store anything. The server is ephemeral and just proxies your request. The only data it even sees is the optional two-letter `language` code if you provide it. Your request is immediately forgotten after the insult is returned.

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