How to Use the Customerly MCP in OpenAI Agents SDK

Build production marketing agents that manage Customerly leads and conversations using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customerly MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync SaaS users with OpenAI Agents SDK

The `create_update_user` MCP tool pushes new signups straight into your marketing stack. Your agent grabs email addresses from your application events and maps them to user profiles automatically. Passing custom attributes lets you segment these cohorts later. Managing lifecycle stages happens through the `add_tag` and `remove_tag` endpoints. When an account hits an onboarding milestone, the agent updates their status instantly. This keeps your messaging logic accurate without manual CSV uploads.

Route support conversations

Pulling active chat threads requires the `list_conversations` and `get_conversation` tools. A specialized triage agent can read incoming user messages, classify the intent, and decide if a human needs to intervene. Handoffs between specialized agents work perfectly here. One model reads the thread, while another triggers a webhook to alert your success team. Built-in guardrails ensure the system never replies to a sensitive ticket before validation.

Clean up stale lead data

Executing the `delete_user` tool purges inactive accounts from your database. You write a safety constraint in your agent definition to verify the user's last login date before proceeding. Handling top-of-funnel prospects works similarly with `create_update_lead`. The system logs anonymous website visitors into the CRM. Full tracing via the OpenAI dashboard lets you audit exactly which prospects the agent touched.

Setup guide

Set up Customerly 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 Customerly tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it into the mcp_servers array when constructing your agent.

Yes. The agent discovers the MCP tools on boot. It maps your incoming data to the required fields and executes updates based on your prompt instructions.

Tag operations happen immediately. Setting cacheToolsList=True reduces startup latency, so your agent fires the tag payload the moment a condition is met.

You control everything through agent instructions and guardrails. If you want a read-only MCP setup, write a rule that explicitly blocks the agent from calling mutation tools.

Your chat conversations and lead emails stay secure within the V8 Isolate Sandbox. Vinkius uses an ephemeral environment that destroys itself after the request finishes, leaving no customer records in memory.

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