Where do I find my Northbeam API credentials?

Log in to your Northbeam Dashboard, navigate to Settings > API Keys. You will find both your API Key and your Data-Client-ID (UUID) there.

Can I download data directly through the agent?

Yes! The `get_export_status` tool will provide a direct download URL once the export status is marked as 'SUCCESS'.

How do I know which metrics I can export?

Use the `list_metrics` and `list_breakdowns` tools to see all valid parameters available for your account before creating a new data export.

Northbeam MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Northbeam
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Northbeam through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Northbeam "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Northbeam?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Northbeam MCP Server

Connect your Northbeam account to your AI agent and gain deep insights into your marketing performance and attribution data through natural conversation.

Pydantic AI validates every Northbeam tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Metric Discovery — List all available performance metrics such as Attributed Revenue, Transactions, and Spend.
Data Breakdowns — Access the labels used to group your data, including Platform, Campaign, Ad Set, and more.
Attribution Modeling — View supported attribution models to understand how credit is assigned across touchpoints.
Programmatic Exports — Initialize new data exports for specific date ranges and sets of metrics.
Export Monitoring — Track the status of your active data exports and retrieve direct download URLs for results.
Workspace Oversight — Monitor active webhooks, scheduled recurring exports, and recent export history.
Account Insights — Access high-level configuration, dashboard settings, and authenticated account metadata.

The Northbeam MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Northbeam to Pydantic AI via MCP

Follow these steps to integrate the Northbeam MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Northbeam with type-safe schemas

Why Use Pydantic AI with the Northbeam MCP Server

Pydantic AI provides unique advantages when paired with Northbeam through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Northbeam integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Northbeam connection logic from agent behavior for testable, maintainable code

Northbeam + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Northbeam MCP Server delivers measurable value.

Type-safe data pipelines: query Northbeam with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Northbeam tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Northbeam and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Northbeam responses and write comprehensive agent tests

Northbeam MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Northbeam to Pydantic AI via MCP:

create_data_export

Initialize a new data export

get_account_info

Get account metadata

get_dashboard_settings

Get workspace dashboard settings

get_export_status

Check data export status

list_attribution_models

g., Clicks only, Modeled). List supported attribution models

list_breakdowns

g., Platform, Campaign, Ad Set) in attribution reports. List available data breakdowns

list_metrics

g., Attributed Revenue, Transactions, Spend) available for export. List available attribution metrics

list_recent_exports

List recently completed exports

list_scheduled_exports

List scheduled data exports

list_webhooks

List active webhooks

Example Prompts for Northbeam in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Northbeam immediately.

"List all the performance metrics available for export in my Northbeam account."

"Check the status of data export ID 'exp_12345'."

"Show me my recent data export history."

Troubleshooting Northbeam MCP Server with Pydantic AI

Common issues when connecting Northbeam to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Northbeam + Pydantic AI FAQ

Common questions about integrating Northbeam MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Northbeam MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.