How to Use the Kustomer MCP in Pydantic AI

Q: What's the setup for Pydantic AI and the Kustomer MCP Server?

It's straightforward. After pip install "pydantic-ai-slimmcp", you create an MCPToolset with your Vinkius server URL. Then you just pass that toolset to your Pydantic AI Agent.

Q: How do I handle complex queries in Kustomer using Pydantic AI?

The searchkustomertimeline tool is your best bet. Your Pydantic AI agent can construct the necessary JSON filter string based on a natural language prompt, and the tool's response will be validated for correctness on return.

Get type-safe, validated Kustomer data in your Python app. Pydantic AI ensures every API response matches your data models.

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 Pydantic AI

Create your Vinkius account to connect Kustomer 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 Kustomer with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Kustomer Data That Won't Break Your App

This isn't just about calling an API; it's about getting data you can trust. When your agent calls `get_customer_profile` or `get_conversation_details`, Pydantic AI validates the response against a Pydantic model at runtime. If Kustomer's API ever returns an unexpected field or a wrong data type, your code will raise a `ValidationError` immediately. No more silent data corruption or chasing down bugs caused by a subtle API change. You know the data's shape is correct, always.

Build Model-Agnostic Support Tools

Pydantic AI is model-agnostic. You can build your Kustomer agent once and run it with OpenAI, Anthropic, Gemini, or a local model. The logic for interacting with Kustomer tools like `list_support_conversations` remains the same. This frees you from vendor lock-in. You can swap out the underlying LLM to find the best fit for your task—maybe one model is better at filtering results from `search_kustomer_timeline`, while another excels at summarizing. Your core application code doesn't change.

Reliably Inspect Kustomer Schemas with this MCP Server

Your support team is always changing things. Use `list_data_klasses` to have your agent check the current custom data schemas in Kustomer. Pydantic AI will parse this into a clean, typed Python object. This lets you build resilient automations. Before running a workflow that depends on a custom field, your agent can verify that the field still exists and has the correct type. It's a proactive way to prevent runtime errors. This MCP Server makes that check simple.

Setup guide

Set up Kustomer 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": {
        "kustomer-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Kustomer 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 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 Pydantic AI

It validates every response from the MCP server against a corresponding Pydantic model. If the JSON from a tool like `get_customer_profile` doesn't match the expected schema, it throws an error instead of letting your app process bad data.

Yes. Pydantic AI is model-agnostic. As long as your model can handle function calling, you can connect it to the Kustomer MCP Server and build your agent locally.

It's straightforward. After `pip install "pydantic-ai-slim[mcp]"`, you create an `MCPToolset` with your Vinkius server URL. Then you just pass that toolset to your Pydantic AI `Agent`.

The `search_kustomer_timeline` tool is your best bet. Your Pydantic AI agent can construct the necessary JSON filter string based on a natural language prompt, and the tool's response will be validated for correctness on return.

Your agent will be able to request Kustomer data including customer profiles, conversation details, and message contents. The connection is proxied through a Vinkius sandbox instance, which encrypts traffic and isolates the session. Your Kustomer API keys are stored server-side, not in your client 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