How to Use the Pylon MCP in OpenAI Agents SDK

Q: How do I install Pylon with the OpenAI Agents SDK?

Run pip install openai-agents in your environment. Initialize the server using MCPServerStreamableHttp and pass it directly to your Agent constructor inside the mcpservers list.

Q: Can I trace Pylon tool execution in the OpenAI dashboard?

Every single tool call, from getissue to replytoissue, appears in your OpenAI developer dashboard. You can inspect the exact payloads and latency for every action initiated by your MCP connection.

Run safe, production-ready B2B support agents with the OpenAI Agents SDK and the Pylon MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Pylon MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Route tickets safely using the Pylon MCP Server

This MCP Server exposes `list_issues` so your OpenAI agents can inspect incoming customer tickets directly. By coupling Pylon's API with the SDK's built-in guardrails, you ensure that agents only fetch open tickets without accidentally mutating customer records. You configure the Pylon server block within an async context manager to feed issues into your OpenAI triage loop. If an agent tries to execute `update_issue` on an account it shouldn't touch, the SDK's validation layer blocks the call before it hits your production database.

Handoff complex accounts between specialized agents

Specialized OpenAI agents can coordinate using `get_account` to pull customer tiers before responding. A triage agent checks the account status and hands the conversation over to an enterprise support agent when a high-value customer flags a critical bug. The secondary agent uses `reply_to_issue` to send targeted updates based on the exact history retrieved via `get_issue_messages`. You get a clean trace of this entire handoff sequence directly inside your OpenAI dashboard.

Draft context-aware replies from your knowledge base

Your agents search internal documentation with `list_knowledge_bases` and `list_articles` to find exact resolutions. This allows the OpenAI Agents SDK to ground its responses in your actual documentation, preventing hallucinated instructions. Once the agent finds the correct article, it drafts a response using `reply_to_issue` to resolve the customer's problem. You can cache the tool list by setting `cacheToolsList=True` to shave off network latency during high-volume support spikes.

Setup guide

Set up Pylon 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 Pylon tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents` in your environment. Initialize the server using `MCPServerStreamableHttp` and pass it directly to your Agent constructor inside the `mcp_servers` list.

Yes, you control this through the SDK's built-in guardrail system. You can intercept calls like `create_issue` or `update_issue` before they execute, ensuring your agents only read data when they should.

The SDK relies on your async context manager to handle network retries. If Pylon limits your `list_issues` calls, the streamable HTTP connection manages the backoff without crashing your agent loop.

Every single tool call, from `get_issue` to `reply_to_issue`, appears in your OpenAI developer dashboard. You can inspect the exact payloads and latency for every action initiated by your MCP connection.

Your B2B support tickets and account details remain inside Pylon's secure database. The SDK only passes the specific JSON strings required for tools like `get_account` through the Vinkius secure MCP sandbox, ensuring zero persistent storage of your customer data.

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