How to Use the Endear Retail CRM MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to the Endear Retail CRM MCP server?

You'll instantiate an MCPServerStreamableHttp client in your Python code, pointing it to your unique Vinkius endpoint URL. Pass that server object into the Agent constructor. The tools are discovered automatically, so there's no manual mapping required.

Q: What's the best way to find a specific customer with an OpenAI Agent and Endear Retail CRM?

The most direct way is using the searchcustomersbynameoremail tool. Just ask your agent to find a customer by their name or email address. It will return a list of matches, which you can then use with getcustomerprofile to get more details.

Q: Can I see my account settings from Endear Retail CRM in my OpenAI Agent?

Yes, the getendearaccountmetadata tool is included for that purpose. It lets your agent retrieve high-level settings and information about your Endear account configuration. This is helpful for agents that need to confirm account status or certain features are enabled.

Give your OpenAI Agent direct access to Endear Retail CRM data, with built-in guardrails for safer, production-ready clienteling.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Endear Retail CRM MCP to OpenAI Agents SDK

Create your Vinkius account to connect Endear Retail CRM 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 Endear Retail CRM with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Full Customer Context Before Acting

Your agent uses `get_customer_profile` to pull a complete picture of a shopper before it does anything. This isn't just a name and email. It's a full history that gives your agent the context it needs to make smart decisions. With that profile, your agent can then dig deeper using `list_customer_purchase_history` and `list_customer_clienteling_notes`. The OpenAI Agents SDK lets you build guardrails around this data. You can write rules that stop the agent from contacting low-value customers or from sending a message that ignores a recent complaint. It's about automating outreach without making costly, impersonal mistakes.

Automate Task and Team Lookups

Connect this MCP Server and your agent can immediately check on your team's workload. It uses `list_clienteling_tasks` to see all open follow-ups and `list_retail_team_members` to know who's on the floor today. This is how you start building agents that don't just find data, but coordinate work. This becomes powerful when you combine tools. For example, an agent can run `quick_retail_performance_audit`, see that sales are down in a category, then find the right product specialist using `list_retail_team_members`, and finally check their open tasks with `list_clienteling_tasks` to see if they have bandwidth for a new assignment. The agent connects the dots for you.

Find Customers and Products Instantly

Stop digging through your CRM manually. Your agent can use `search_customers_by_name_or_email` to pinpoint a specific person in seconds. It's a direct line into your customer database, ready for any conversational query. The agent gets the ID and can immediately start pulling their history. It works for products, too. An agent can call `list_retail_products` to check inventory or find details about a specific item. This is useful for building internal tools. A sales associate can ask the agent, "Do we have this jacket in a medium?" and get an immediate, accurate answer without leaving their chat client.

Setup guide

Set up Endear Retail CRM 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 Endear Retail CRM tools at runtime.
3

Create your Agent

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

Run the agent

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

You'll instantiate an `MCPServerStreamableHttp` client in your Python code, pointing it to your unique Vinkius endpoint URL. Pass that server object into the `Agent` constructor. The tools are discovered automatically, so there's no manual mapping required.

No, this MCP server provides read-only access to your Endear data. Your agent can use tools like `list_retail_customers` and `get_customer_profile` to read information, but it cannot create, update, or delete any records. This is a deliberate security measure.

The most direct way is using the `search_customers_by_name_or_email` tool. Just ask your agent to find a customer by their name or email address. It will return a list of matches, which you can then use with `get_customer_profile` to get more details.

Yes, the `get_endear_account_metadata` tool is included for that purpose. It lets your agent retrieve high-level settings and information about your Endear account configuration. This is helpful for agents that need to confirm account status or certain features are enabled.

This server only provides read-only access to Endear data like customer profiles, purchase history, and clienteling notes. The OpenAI framework adds another layer, letting you define guardrails that can prevent the agent from even attempting to access or share sensitive PII before an action is executed. All traffic is sent over HTTPS.

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