How to Use the Northbeam MCP in Pydantic AI

Q: How does Pydantic AI ensure my Northbeam data is correct?

Every time your agent calls a Northbeam tool, like listrecentexports, Pydantic AI automatically parses the JSON response into a Pydantic model. If any data from the MCP server is missing or has the wrong type, it raises an error instantly.

Q: What happens if the Northbeam API changes unexpectedly with Pydantic AI?

Your application will fail loudly with a ValidationError. This is a feature. It prevents your Pydantic AI agent from processing bad data from Northbeam and protects your application from silent failures.

Q: Is it easy to connect Pydantic AI to the Northbeam MCP server?

Yes, it's a one-liner. You just instantiate the MCPToolset with your Vinkius server URL and pass it to your Pydantic AI Agent. It handles the rest.

Get type-safe, validated Northbeam attribution data in your Python app with Pydantic AI. No more silent data corruption.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Northbeam MCP to Pydantic AI

Create your Vinkius account to connect Northbeam 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 Northbeam with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Reports That Don't Break

Use any LLM you want to decide which report to run. Your agent can reason over the output of `list_metrics` and `list_breakdowns` to choose the right combination for a new report. Here's the key: when your agent calls `create_data_export`, Pydantic AI validates the response from the Northbeam server. If the API returns anything unexpected—a missing field, a wrong data type—your code will raise a `ValidationError` immediately. No more chasing down bugs caused by bad data.

Trust Your Export Status Checks

Polling for data exports requires clean, predictable state changes. Your agent uses `get_export_status` to monitor a job's progress from 'queued' to 'completed'. With Pydantic AI, the response from `get_export_status` is guaranteed to match your Pydantic model. You know for a fact whether the status string is valid and if the `export_id` is present. Your monitoring loop just became 100% more reliable.

Configure Northbeam with any MCP Server

Your agent can pull all available attribution models using `list_attribution_models`. You can then present this list to a user or use it to configure your reporting logic. Pydantic AI ensures the list of models is correctly parsed into a Python object you can trust. Since Pydantic AI is model-agnostic, you can use this validated data with an agent powered by GPT-4, Claude 3, or a local Llama model without changing your tool code.

Setup guide

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

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

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

Every time your agent calls a Northbeam tool, like `list_recent_exports`, Pydantic AI automatically parses the JSON response into a Pydantic model. If any data from the MCP server is missing or has the wrong type, it raises an error instantly.

Yes. Pydantic AI is model-agnostic. You can connect to the Northbeam MCP server and use it with agents powered by OpenAI, Anthropic, or any model you run locally. The tool validation works the same everywhere.

Your application will fail loudly with a `ValidationError`. This is a feature. It prevents your Pydantic AI agent from processing bad data from Northbeam and protects your application from silent failures.

Yes, it's a one-liner. You just instantiate the `MCPToolset` with your Vinkius server URL and pass it to your Pydantic AI `Agent`. It handles the rest.

It only handles your Northbeam attribution data—things like campaign performance metrics, revenue, and spend. Your data is processed in an ephemeral V8 isolate, and Pydantic models add a layer of application-level security by rejecting malformed data before it ever enters your system.

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