How to Use the Baremetrics MCP in Pydantic AI

Q: How do I add the Baremetrics tools to my Pydantic AI agent?

You'll use the MCPToolset class. Just initialize it with your Vinkius endpoint URL for this server, then pass the toolset object into the toolsets list when creating your Agent. It's a single line of code.

Get type-safe, validated Baremetrics data in your Python agent with 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 Baremetrics MCP to Pydantic AI

Create your Vinkius account to connect Baremetrics 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 Baremetrics with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Customer Data, Guaranteed

This toolset lets you fetch customer information from Baremetrics. You can `list_customers` to get everyone, or use `get_customer` to find one person by their ID or email. The `list_subscriptions` tool gives you their full subscription history. Pydantic AI's strength is runtime validation. If Baremetrics ever changes an API field or your agent hallucinates a parameter, the tool call fails with a clear `ValidationError`. No more silent data corruption—you know immediately when the data doesn't match the Pydantic model you expect.

Reliably Track Financial Metrics

Your agent can pull key financial data with total confidence in the output schema. Use `get_mrr`, `get_ltv`, and `get_churn_rate` for top-line numbers. For more detail, `get_metric` lets you request specific values like `active_subscriptions` or `failed_charges`. Every response from this MCP Server is parsed by Pydantic AI before your agent sees it. If a number comes back as a string or a required field is missing, your code will raise an exception. This enforces strict correctness for any financial reporting or analysis you build.

A Model-Agnostic MCP Toolset

This Baremetrics toolset works with any LLM Pydantic AI supports. Whether you're using OpenAI, Anthropic, Gemini, or a local model, the tool-calling logic remains the same. The `MCPToolset` class abstracts away the connection details. Setup is clean. You import `MCPToolset`, point it to your Vinkius server URL, and pass it to your `Agent`. Pydantic AI handles the HTTP requests and, most importantly, the response validation. It's a solid foundation for building agents that have to be right.

Setup guide

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

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

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

The main reason is correctness. Pydantic AI validates every response from the Baremetrics server against a Pydantic model. If the data isn't structured exactly as expected, it fails loudly, which is critical when you're working with financial data.

You'll use the `MCPToolset` class. Just initialize it with your Vinkius endpoint URL for this server, then pass the toolset object into the `toolsets` list when creating your `Agent`. It's a single line of code.

No, it's model-agnostic. Pydantic AI works with models from OpenAI, Google, Anthropic, and others. You can swap out the LLM without changing how your agent uses the Baremetrics tools.

Pydantic AI generates the models automatically based on the OpenAPI schema provided by the MCP Server. While you don't have to write them yourself, you can inspect the generated tool schemas to see exactly what data structure to expect for calls like `get_customer` or `list_metrics`.

This server handles your Baremetrics customer and subscription records. The real security benefit with Pydantic AI is data integrity. Every piece of financial data returned is parsed and validated against your Pydantic models, stopping corrupted financial data from ever reaching your agent's logic.

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