How to Use the Postman MCP in OpenAI Agents SDK

Q: Does this work with specialized agent handoffs?

Yes. You might have one agent run listmocks to find test servers, then hand the mock URL off to a testing agent. The handoff preserves the fetched data perfectly.

Give your production agents native Postman API access with zero configuration using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Postman MCP to OpenAI Agents SDK

Create your Vinkius account to connect Postman to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Postman with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Map API architectures autonomously

`list_workspaces` and `get_workspace_details` let your agent map out your entire API catalog before taking action. You build specialized agents that hand off tasks. One agent maps the workspace, another pulls specific endpoints. By feeding these details into OpenAI's built-in guardrails, you ensure your agents never mutate the wrong endpoint. They just read the structure and pass the validated schema down your production pipeline.

Postman MCP Server integration for environments

`list_environments` and `get_environment_details` pull your dev and prod variables directly into your agent's context window. Your AI client reads the exact tokens and URLs your team actually uses. There is no guessing which base URL applies. You set up an agent to validate staging configurations, and it checks the live Postman environment data against your deployed services.

Extract raw request payloads

`list_collections` and `get_collection_details` extract raw request payloads from your API definitions. Your agent reads the exact JSON structures required to hit an endpoint. When a test fails in production, your tracing dashboard shows exactly which collection the agent pulled. It grabs the request data, formats it, and runs diagnostics without manual intervention.

Setup guide

Set up Postman 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 Postman tools at runtime.
3

Create your Agent

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

Run the agent

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

Run pip install openai-agents. Create an MCPServerStreamableHttp instance with your Vinkius URL. Pass it into your Agent constructor using the mcp_servers array.

Yes. Once you pass the MCP Server to the constructor, the SDK automatically registers all nine endpoints. Set cacheToolsList=True to speed up initialization.

You rely on Vinkius endpoint tokens and OpenAI guardrails. The agent only sees what the token allows. You write instructions to prevent the agent from querying specific workspace IDs.

Yes. You might have one agent run `list_mocks` to find test servers, then hand the mock URL off to a testing agent. The handoff preserves the fetched data perfectly.

Your environment variables pass through an ephemeral V8 Isolate Sandbox. We do not store your `get_environment_details` payloads. The zero-trust architecture destroys the execution context immediately after your AI client receives the variable values.

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