How to Use the Metronome MCP in Pydantic AI

Q: How do I initialize the Metronome MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp and use the MCPToolset class pointed at your Vinkius HTTP endpoint. Pass this toolset directly into the toolsets list when defining your type-safe agent.

Q: Can I use Pydantic AI to validate custom field keys in Metronome?

Yes. When using addcustomfieldkey or setcustomfieldvalues, you can enforce strict schemas on the key-value pairs to ensure your metadata always matches your internal database requirements.

Q: Does this toolset support asynchronous event ingestion?

Yes. You can run async loops to call ingestevents continuously, relying on the framework's runtime validation to keep your high-throughput MCP pipeline clean and error-free.

Build bulletproof, type-safe billing agents with Pydantic AI and the Metronome MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metronome MCP to Pydantic AI

Create your Vinkius account to connect Metronome 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 Metronome with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe contract generation via MCP Server tools

The `create_contract` tool requires strict parameter formatting, which this framework validates at runtime before making the API call. If your agent attempts to pass an invalid rate card ID or a malformed date, Pydantic AI raises a validation error immediately. This strict checking prevents invalid data from corrupting your Metronome contracts. You don't have to worry about silent failures where an agent hallucinates a pricing tier that doesn't exist in your catalog.

Guaranteed invoice parsing and generation

The `get_invoice` tool returns highly structured billing data that your Pydantic AI agent can parse directly into typed Python schemas. When regenerating billing runs, the agent uses `regenerate_invoice` and validates the output structure to ensure no line items were dropped. If the Metronome API schema changes or returns unexpected null values, the agent fails loudly instead of processing a bad invoice. This gives you complete confidence that your automated billing runs match your accounting models.

Validated usage event ingestion

The `ingest_events` tool expects precise event payloads to handle up to 100,000 events per second without dropping records. Your agent validates every usage event against a Pydantic model before calling the ingestion tool, catching schema drift at the source. By running these checks locally in Python, you avoid wasting API quota on malformed events. The agent can immediately flag bad data inputs using `search_events` to locate the source of the formatting error.

Setup guide

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

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

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

Install `pydantic-ai-slim[mcp]` and use the `MCPToolset` class pointed at your Vinkius HTTP endpoint. Pass this toolset directly into the `toolsets` list when defining your type-safe agent.

The framework will raise a validation error at runtime, forcing the agent to stop execution. This prevents downstream tasks from processing corrupt customer profiles or incorrect invoice totals.

Yes. When using `add_custom_field_key` or `set_custom_field_values`, you can enforce strict schemas on the key-value pairs to ensure your metadata always matches your internal database requirements.

Yes. You can run async loops to call `ingest_events` continuously, relying on the framework's runtime validation to keep your high-throughput MCP pipeline clean and error-free.

The MCP Server secures your Metronome credentials, contract details, and customer usage data using Vinkius's ephemeral V8 sandboxes. The framework never exposes your API keys to the model, maintaining a strict zero-trust boundary between the agent's reasoning engine and your financial data.

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