How to Use the Endear Retail CRM MCP in Pydantic AI

Q: How do I set up Pydantic AI with the Endear Retail CRM server?

First, pip install "pydantic-ai-slimmcp". Then, create an MCPToolset instance, passing your Vinkius server URL as the first argument. You add this toolset to the toolsets list when you create your Agent.

Q: What happens if the Endear API returns data Pydantic AI doesn't expect?

Your agent will raise a ValidationError immediately. This is the core benefit of Pydantic AI—it prevents your agent from working with malformed or unexpected data. You'll know instantly that the API response didn't match your Pydantic model.

Q: Can I use Pydantic AI to read my team's notes in Endear Retail CRM?

Yes, absolutely. The listcustomerclientelingnotes tool is designed for this. When your agent uses it, Pydantic AI will validate that each note returned from the API matches your predefined schema for what a clienteling note should look like.

Q: How do I get a list of all my customers using Pydantic AI and Endear Retail CRM?

Your agent would use the listretailcustomers tool. Pydantic AI will automatically handle calling the tool and parsing the list of customers into structured Pydantic objects for you to use in your code.

Build agents that interact with Endear Retail CRM and never fail silently, thanks to Pydantic AI's runtime data validation.

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 Pydantic AI

Create your Vinkius account to connect Endear Retail CRM to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe Customer Profiles

Your agent can call `get_customer_profile` or `search_customers_by_name_or_email` to fetch customer data from Endear. The real difference with Pydantic AI is that the response is immediately parsed and validated against a Pydantic model. You get a clean, typed object to work with, every time. This means no more defensive coding or checking for missing keys. If the Endear API ever returns an unexpected data structure, your code will raise a `ValidationError` instantly. You build more reliable agents because you can trust the shape of the data you're processing, whether it's from `list_customer_purchase_history` or `list_customer_clienteling_notes`.

Manage Tasks with Guaranteed Correctness

Use the `list_clienteling_tasks` tool to pull all open follow-ups into your agent. Pydantic AI ensures that every task it receives from the MCP Server fits the exact schema you've defined. There's no chance of your agent misinterpreting a due date or task description. This structural guarantee is critical when you're building automated systems. You can confidently have your agent loop through tasks, check team availability with `list_retail_team_members`, and prepare reports, knowing that a malformed API response won't cause silent data corruption down the line. It either works correctly, or it fails loudly.

Build Model-Agnostic Retail Agents

This MCP server exposes 10 tools for Endear. With Pydantic AI, you can use these tools with any LLM you want—OpenAI, Anthropic, Gemini, or a local model. Your tool logic remains completely separate from the model provider. Your code for interacting with `list_retail_products` or running a `quick_retail_performance_audit` doesn't change if you switch LLMs. Pydantic AI handles the model-specific prompting and function calling for you. This lets you focus on your application's logic and choose the best LLM for the job without rewriting your tool integrations.

Setup guide

Set up Endear Retail CRM MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "endear-retail-crm-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Endear Retail CRM tools.",
)

result = await agent.run("List recent Endear Retail CRM transactions")
print(result.output)

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 Pydantic AI

First, `pip install "pydantic-ai-slim[mcp]"`. Then, create an `MCPToolset` instance, passing your Vinkius server URL as the first argument. You add this toolset to the `toolsets` list when you create your `Agent`.

Your agent will raise a `ValidationError` immediately. This is the core benefit of Pydantic AI—it prevents your agent from working with malformed or unexpected data. You'll know instantly that the API response didn't match your Pydantic model.

Yes, absolutely. The `list_customer_clienteling_notes` tool is designed for this. When your agent uses it, Pydantic AI will validate that each note returned from the API matches your predefined schema for what a clienteling note should look like.

Your agent would use the `list_retail_customers` tool. Pydantic AI will automatically handle calling the tool and parsing the list of customers into structured Pydantic objects for you to use in your code.

The MCP server provides read-only access to Endear data like customer profiles and purchase history. Pydantic AI adds a structural security layer on top of that. By enforcing strict data models, it helps prevent data leakage or misinterpretation by ensuring your agent only processes data that exactly matches the format you expect.

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