How to Use the Modal (Serverless AI Infrastructure) MCP in OpenAI Agents SDK

Q: How do I configure the Modal (Serverless AI Infrastructure) toolset inside OpenAI Agents SDK?

Install openai-agents first. Pass the MCPServerStreamableHttp instance pointing to your Vinkius endpoint directly into your agent's constructor. The SDK automatically discovers all seven tools via the MCP protocol.

Q: Can OpenAI Agents SDK automatically kill hung jobs on Modal (Serverless AI Infrastructure)?

Yes, your agent can monitor run times and call stopapp when a task hangs. You write the evaluation logic, and the agent executes the shutdown.

Q: Does the Modal (Serverless AI Infrastructure) integration with OpenAI Agents SDK support tracing?

Every tool call like getapp shows up in your OpenAI dashboard automatically. You get full visibility into what the agent requested and what the serverless API returned.

Q: How does the agent handle multiple environments?

The agent uses listapps to query active or historical contexts across your workspace. This lets you partition your testing and production deployments cleanly.

Deploy self-healing GPU workloads with OpenAI Agents SDK managing your serverless Modal infrastructure under strict safety guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modal (Serverless AI Infrastructure) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control runaway serverless compute using our MCP Server

This MCP Server exposes direct execution controls like `stop_app` to let your agents kill stuck GPU jobs instantly. When an agent detects a timeout in your inference pipeline, it immediately triggers this endpoint to prevent runaway cloud bills. You set the hard cost limits in your Python code. The OpenAI Agents SDK runs these checks before executing any tool call, ensuring your agent never leaves a rogue container running overnight.

Audit active GPU deployments dynamically

The `list_deployments` tool retrieves the live state of your active model endpoints directly from the platform. Your agent calls this to verify that the target GPU configuration is active before routing production traffic. Tracing displays these environment checks directly inside your OpenAI developer dashboard. You see every single call to `get_deployment` alongside your standard model logs, giving you a clear timeline of your infrastructure state.

Inspect storage volumes and secrets safely

The `list_volumes` tool exposes your attached network storage blocks so the agent can confirm data availability. It maps these volumes to active runs without exposing the raw data payloads to the model. Security policies restrict the agent to reading metadata via `list_secrets` instead of raw values. This design prevents sensitive API keys from leaking during MCP interactions.

Setup guide

Set up Modal (Serverless AI Infrastructure) 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 Modal (Serverless AI Infrastructure) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` first. Pass the `MCPServerStreamableHttp` instance pointing to your Vinkius endpoint directly into your agent's constructor. The SDK automatically discovers all seven tools via the MCP protocol.

Yes, your agent can monitor run times and call `stop_app` when a task hangs. You write the evaluation logic, and the agent executes the shutdown.

Every tool call like `get_app` shows up in your OpenAI dashboard automatically. You get full visibility into what the agent requested and what the serverless API returned.

The agent uses `list_apps` to query active or historical contexts across your workspace. This lets you partition your testing and production deployments cleanly.

This server only accesses metadata like application run IDs, volume names, and secret configuration keys. No raw model weights or private database records ever pass through the Vinkius gateway.

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