Where do I find my Kustomer API Key?

Log in to Kustomer, navigate to **Settings** > **Security** > **API Keys**, and create a new key with the necessary scopes.

Can I see chat messages in real-time?

The `list_conversation_messages` tool fetches the current history. While not a streaming 'live' view, it provides the most recent state.

Does this support creating customers?

The current version focus on data retrieval and analysis. Creation tools are planned for future updates.

Kustomer MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Kustomer
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Kustomer through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Kustomer "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Kustomer?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kustomer MCP Server

Connect your AI agent to Kustomer to streamline your support operations and customer data auditing.

Pydantic AI validates every Kustomer tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Omnichannel Conversation Access — List and audit support conversations from email, chat, and social channels
Customer 360 View — Fetch detailed customer profiles including custom attributes and history
Message Auditing — Retrieve the full message history for any support interaction
Timeline Search — Perform deep searches across customer timelines using complex JSON filters
Service Context — List support queues, agents, and custom data classes (Klasses)

Simple Setup

1. Subscribe to this server
2. Log in to Kustomer and generate a Bearer API Key (Settings > Security > API Keys)
3. Enter your key in the configuration panel
4. Start managing your support data via natural language

The Kustomer MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kustomer to Pydantic AI via MCP

Follow these steps to integrate the Kustomer MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Kustomer with type-safe schemas

Why Use Pydantic AI with the Kustomer MCP Server

Pydantic AI provides unique advantages when paired with Kustomer through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Kustomer integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Kustomer connection logic from agent behavior for testable, maintainable code

Kustomer + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Kustomer MCP Server delivers measurable value.

Type-safe data pipelines: query Kustomer with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Kustomer tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Kustomer and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Kustomer responses and write comprehensive agent tests

Kustomer MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Kustomer to Pydantic AI via MCP:

check_kustomer_api_status

Check the status of the Kustomer API

get_conversation_details

Get details for a specific conversation

get_customer_profile

Get details for a specific customer

list_conversation_messages

List all messages in a conversation

list_data_klasses

List Kustomer custom data classes (Klasses)

list_kustomer_agents

List all support agents (users)

list_kustomer_customers

Essential for identifying customer IDs for support auditing. List all customers in Kustomer

list_support_conversations

List recent support conversations

list_support_queues

g., Billing, Technical Support) defined in Kustomer. List active support queues

search_kustomer_timeline

Provide filters as a JSON string. Perform a deep search across the customer timeline

Example Prompts for Kustomer in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Kustomer immediately.

"List the 10 most recent support conversations in Kustomer"

"Show the full profile for customer '65a4b3c2d1e0f'"

"Search the timeline for customers from 'Brazil'"

Troubleshooting Kustomer MCP Server with Pydantic AI

Common issues when connecting Kustomer to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Kustomer + Pydantic AI FAQ

Common questions about integrating Kustomer MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Kustomer MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.