Can I check my API gateway metrics through the agent?

Yes. The `get_metrics` tool allows your AI agent to retrieve real-time traffic and latency data for any specific project ID, helping you monitor gateway performance directly through chat.

How do I create a new consumer identity for API key authentication?

You can use the `create_consumer` tool. Provide the project ID and a JSON payload with the consumer's details, and Zuplo will provision the new identity for your API gateway instantly.

Is it possible to see my project's configuration files via conversation?

Absolutely. Use the `list_project_files` tool to retrieve the declarative configuration files for your API project, allowing you to audit routing and policy definitions through your agent.

Zuplo MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Zuplo
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Zuplo through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Zuplo Assistant",
            instructions=(
                "You help users interact with Zuplo. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Zuplo"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Zuplo MCP Server

Connect your Zuplo account to any AI agent and manage your programmable API infrastructure through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Zuplo through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Zuplo, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Project Management — List all Zuplo projects and API gateways in your account to monitor your integration landscape
Edge Deployments — Trigger new configuration deployments to the global edge network or audit previous deployment history
Consumer Governance — Create, manage, and revoke API key consumers to control who has access to your gateway authentication
Environment Auditing — List available project environments (e.g., working, production) and verify their current operational status
DNS & Domains — Retrieve and manage configured custom DNS domains for each of your API projects directly from your agent
Real-Time Metrics — Monitor gateway traffic, latency, and throughput metrics directly from Zuplo's edge analytics network
Declarative Config — Browse and list the configuration files that define your gateway's routing and policy logic

The Zuplo MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Zuplo to OpenAI Agents SDK via MCP

Follow these steps to integrate the Zuplo MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Zuplo

Why Use OpenAI Agents SDK with the Zuplo MCP Server

OpenAI Agents SDK provides unique advantages when paired with Zuplo through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Zuplo + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Zuplo MCP Server delivers measurable value.

Automated workflows: build agents that query Zuplo, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Zuplo, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Zuplo tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Zuplo to resolve tickets, look up records, and update statuses without human intervention

Zuplo MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Zuplo to OpenAI Agents SDK via MCP:

create_consumer

Create API key consumer

create_deployment

Create a new deployment

delete_consumer

Delete API key consumer

get_metrics

Get edge metrics

list_consumers

List API key consumers

list_custom_domains

List custom domains

list_deployments

List deployments

list_environments

g., working, production) for a Project. List project environments

list_files

List configuration files

list_projects

List Zuplo projects

Example Prompts for Zuplo in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Zuplo immediately.

"List all my Zuplo projects."

"Check the latency metrics for 'proj-101'."

"Create a new consumer for 'Acme Partner' in project 'proj-101'."

Troubleshooting Zuplo MCP Server with OpenAI Agents SDK

Common issues when connecting Zuplo to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Zuplo + OpenAI Agents SDK FAQ

Common questions about integrating Zuplo MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.