How to Use the Upzelo MCP in Pydantic AI

Q: Can I list all customers using Upzelo with Pydantic AI?

Yes. The listcustomers tool provides a reliable list of customer records. This makes sure that the data you pass to your agent is always correctly typed and structured.

Q: What kind of subscription management does Upzelo offer for Pydantic AI?

You can retrieve plan details using getsubscription or change them with updatesubscription. The validation layer ensures that the data returned by these tools is perfectly structured.

Secure Upzelo Automation using your Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Upzelo MCP to Pydantic AI

Create your Vinkius account to connect Upzelo 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 Upzelo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Customer Data via MCP Server

The `get_customer` tool lets your agent fetch specific user details. Because of Pydantic validation, if the API response is messy, your agent fails loudly—no silent corruption. You can list all records with `list_customers`, or refine targeting by calling `save_customer`.

Control Retention Flows with Upzelo

Need to start a retention effort? Call the `start_flow` tool. The agent handles initiating personalized offers that aim to win back customers at exit points. Tracking is easy; use `get_flow_session` to check status, or run `list_flows` to see all available sequences.

Handle Subscriptions and Accounts

Use the `get_subscription` tool to get account details. Pydantic ensures that whatever plan data comes back is structured correctly for your code. Updates are handled with `update_subscription`. The `list_subscriptions` tool gives a validated list of all service tiers.

Setup guide

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

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

result = await agent.run("List recent Upzelo 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 Upzelo. 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 Upzelo 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 Upzelo MCP in Pydantic AI

The MCP Server provides tools for sales automation. Because you are using the type-safe framework, every response from tools like `get_customer` is validated against your defined models before your agent processes it.

Yes. The `list_customers` tool provides a reliable list of customer records. This makes sure that the data you pass to your agent is always correctly typed and structured.

You can retrieve plan details using `get_subscription` or change them with `update_subscription`. The validation layer ensures that the data returned by these tools is perfectly structured.

It's ideal. If correctness matters more than speed, this setup delivers. The MCP Server feeds validated tool outputs directly into your agent's workflow.

This server handles customer records and subscription attributes. Specifically, it deals with identifying details from `get_customer` and plan information found in the `list_subscriptions` tool.

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