How to Use the Kustomer MCP in OpenAI Agents SDK

Q: What's the best way to search conversations with an OpenAI agent in Kustomer?

Use the searchkustomertimeline tool. Your agent can construct a JSON filter string based on the user's request, letting you find conversations by status, channel, or custom fields without needing to know the Kustomer query language yourself.

Connect your OpenAI Agent to Kustomer for production-ready, auditable customer support actions with built-in 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 Kustomer MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Customer History with Guardrails

Your agent can pull a complete customer history without writing a single line of API code. It uses `get_customer_profile` to find a user, then `list_support_conversations` to see their tickets. The OpenAI SDK automatically discovers these tools on the MCP Server. The real value here is the safety. The SDK's guardrails can validate the agent's plan before it ever touches Kustomer data, preventing accidental data changes. You get full execution traces in your dashboard, so you always know what your agent did and why.

Triage and Route Conversations

Build an agent that intelligently routes incoming support requests. It can `list_support_queues` to see where tickets can go, then use `search_kustomer_timeline` with specific filters to understand the context of a new conversation. Your OpenAI Agent can hand off complex tickets to a specialized human agent or another AI agent. This isn't just a simple script; it's a multi-agent system where you define the rules of engagement, and the SDK handles the handoffs and state management.

Monitor Kustomer API and Data Schemas with this MCP Server

Before your agent does anything, it can run a pre-flight check using `check_kustomer_api_status`. This prevents failed jobs and wasted cycles if the Kustomer API is down. It's a simple step that adds a lot of reliability to your production system. Your agent can also inspect Kustomer's custom data structures with `list_data_klasses`. This is critical for building automations that don't break when someone on the support team adds a new field. Your agent adapts instead of failing silently.

Setup guide

Set up Kustomer 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 Kustomer tools at runtime.
3

Create your Agent

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

Run the agent

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

It's automatic. When you pass the Kustomer MCP Server to the Agent constructor, it fetches the tool manifest and makes them available. Set `cacheToolsList=True` so it only has to do this once per session.

Yes. You define the agent's permissions and can use the built-in guardrails to create policies that restrict access. For example, you can allow `get_customer_profile` but block timeline searches for certain agent types.

Vinkius handles it. You get a single endpoint token for the MCP Server. Your agent uses that token, and the server manages the Kustomer API credentials securely.

Use the `search_kustomer_timeline` tool. Your agent can construct a JSON filter string based on the user's request, letting you find conversations by status, channel, or custom fields without needing to know the Kustomer query language yourself.

This server only accesses Kustomer data like customer profiles, conversation histories, and message content. Your Vinkius endpoint is ephemeral and isolated, and all authentication tokens are managed on the server, not in your agent's code.

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