How to Use the Customerly MCP in Pydantic AI

Q: How do I initialize the Customerly MCP Server with Pydantic AI?

Install the pydantic-ai-slimmcp package. Initialize an MCPToolset with your Vinkius HTTP URL, then pass it to the toolsets array on your Agent.

Build type-safe Customerly workflows with Pydantic AI where every user update is strictly validated.

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 Pydantic AI

Create your Vinkius account to connect Customerly 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 Customerly with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarantee accurate user profiles

The `create_update_user` tool forces your agent to supply exactly what the API expects. Pydantic AI validates the email format and custom attributes before the MCP network request ever fires. Managing prospects with `create_update_lead` follows the same strict rules. If the language model hallucinates a required field, the framework throws a loud validation error instead of silently corrupting your database.

Read chats with Pydantic AI MCP Server

Pulling support threads relies on `list_conversations` and `get_conversation`. The framework parses the incoming JSON payload into strict Python objects, ensuring your agent never chokes on unexpected null values. Building analytical workflows becomes much safer this way. Your agent extracts the exact message timestamps and sender IDs it needs to calculate response times accurately.

Enforce strict tag management

Triggering `add_tag` requires precise contact identification. You define the exact string literal constraints for tag names, preventing the model from inventing random categories. Cleaning up old categories uses `remove_tag` or even `delete_user` for full purges. Because you passed the MCP toolset to the agent, it knows exactly which operations are valid and which parameters are mandatory.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package. Initialize an MCPToolset with your Vinkius HTTP URL, then pass it to the toolsets array on your Agent.

Yes. The framework enforces strict schema matching. If the API returns a malformed response, your system fails loudly rather than passing bad data downstream.

It works with any supported provider. Pydantic AI is model-agnostic, so you can run Llama locally to classify tickets and trigger updates.

Both Streamable HTTP and SSE transports are fully supported. The unified toolset approach handles the connection mechanics automatically.

Your prospect emails and custom attributes never touch persistent storage. Vinkius handles the auth routing through an ephemeral V8 sandbox that evaporates the moment the sync finishes.

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