Where do I find my primary Tray.io Access Token?

Log in precisely through your Tray.io admin interface. Focus toward the user settings and click heavily on 'Profile' located usually top-right corner or bottom-left depending on your tier. Inside, shift directly to Personal Access Tokens to view the encoded array. Keep generated values incredibly safe as they orchestrate mass systems.

How important is defining the TRAY_REGION property?

The API fundamentally varies endpoints based on your region (e.g., `us1`, `eu1`, `apac1`). If unassigned or blank, it legally defaults to `us1`. If your instance is physically nested anywhere else in global scope, you must insert your region, or your API logs will constantly fail resolving token access domains.

Should I use a User Token or a Master Token for the Tray MCP?

You must use the Master Token. The Master Token acts as an administrative key allowing you to list authentications and orchestrate workflows across your organization's workspace, whereas a User Token is restricted.

Tray.io MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: Tray.io
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Tray.io 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="Tray.io Assistant",
            instructions=(
                "You help users interact with Tray.io. "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Tray.io"
        )
        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 Tray.io MCP Server

Connect your AI agent exclusively to your Tray.io (or Tray.ai) integration workflows. Bypass cumbersome cloud panels and directly manage automations, integrations, and solutions within a conversational interface. Allow your operations team or architects to audit workflows and supervise massive data transfer nodes organically, checking for health or broken loops in plain text.

The OpenAI Agents SDK auto-discovers all 6 tools from Tray.io through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Tray.io, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Inventory Verification — Audit all current integration solutions, mapping how data moves inside the entire architectural setup instantly
Workflow Discovery — Instantly list and read metadata components or current triggers attributed to single active workflows
Live Monitoring — Investigate the execution history logs on specific workflows to strictly certify which nodes succeeded or crashed during testing
Component Assessment — Browse global lists of ready-to-use Connectors (like Salesforce, Stripe, Zendesk) directly out of your machine before mapping an integration strategy
Session Integrity — Ping the core system to evaluate user identity tokens, boundaries, and regional connections to guarantee uptime

The Tray.io MCP Server exposes 6 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 Tray.io to OpenAI Agents SDK via MCP

Follow these steps to integrate the Tray.io 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 6 tools from Tray.io

Why Use OpenAI Agents SDK with the Tray.io MCP Server

OpenAI Agents SDK provides unique advantages when paired with Tray.io 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

Tray.io + OpenAI Agents SDK Use Cases

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

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

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

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

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

Tray.io MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect Tray.io to OpenAI Agents SDK via MCP:

get_authenticated_user

Retrieves details for the currently authenticated user

get_workflow_details

Retrieves details for a specific Tray.io workflow

list_available_connectors

g., Salesforce, Slack) can be integrated. Lists all available service connectors in Tray.io

list_integration_solutions

Lists all solutions (integration templates) in the account

list_workflow_executions

Lists recent execution history for a specific workflow

list_workflows

Lists all workflows in the Tray.io account

Example Prompts for Tray.io in OpenAI Agents SDK

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

"List all active workflows in my account right now."

"Can you check the latest execution history for workflow wf-a1b2?"

Troubleshooting Tray.io MCP Server with OpenAI Agents SDK

Common issues when connecting Tray.io 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.

Tray.io + OpenAI Agents SDK FAQ

Common questions about integrating Tray.io 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.