How to Use the Measured MCP in Pydantic AI

Q: How does Pydantic AI validate the data returned by Measured?

When your agent calls tools like getperformancesummary, the framework maps the JSON response from the MCP Server directly to a Pydantic schema. If any field violates the expected type, the agent raises a validation error immediately.

Q: Can my agent identify broken data connections?

Yes. The agent can call listintegrations to fetch the status of your active data pipelines. If a connection is failing, the agent detects the anomaly and can halt downstream reporting tasks.

Validate every Measured attribution metric at runtime using Pydantic AI to prevent corrupt marketing data from breaking your pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Measured MCP to Pydantic AI

Create your Vinkius account to connect Measured 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 Measured with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe marketing analytics with Pydantic AI

The `get_performance_summary` tool retrieves your cross-channel marketing metrics directly into your type-safe Python application. Because Pydantic AI validates every incoming payload, any unexpected schema changes in your ad data will trigger an immediate runtime error instead of silently corrupting your reports. Your agent uses this strict validation to parse campaign metrics retrieved via `get_campaign_performance`. If an ad network returns a malformed string instead of a float for ROAS, the framework catches it instantly, ensuring your calculations remain mathematically sound.

Strict schema validation for your MCP Server

The `get_incrementality_scores` tool exposes the true business lift of your marketing channels. When your agent queries these scores, Pydantic AI enforces strict data models on the response, ensuring your agent never makes budget decisions based on incomplete data. This model-agnostic validation applies to all tools, including `get_insights` and `list_reports`. You can swap your underlying LLM provider at any time, knowing that the data schemas returned by the server will remain consistent and fully typed.

Automated integration tracking and verification

The `list_integrations` tool lets your agent audit your active data connections to ensure tracking integrity. Your agent can cross-reference these integrations with your active platforms using `list_channels` to verify that every dollar spent is accounted for. By running this check inside a Pydantic AI agent, you guarantee that the channel structures match your internal database types. The agent can confidently query `get_performance_by_channel` knowing that the channel identifiers are validated before any API calls are executed.

Setup guide

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

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

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

When your agent calls tools like `get_performance_summary`, the framework maps the JSON response from the MCP Server directly to a Pydantic schema. If any field violates the expected type, the agent raises a validation error immediately.

No. The MCPToolset class automatically discovers the tools and registers their schemas at runtime. Your Pydantic AI agent can immediately call `get_incrementality_scores` or `get_insights` without manual schema definition.

Yes. The Vinkius-hosted MCP Server supports async HTTP transports, allowing your Pydantic AI agent to query `get_campaign_performance` for multiple campaigns in parallel without blocking your main application loop.

Yes. The agent can call `list_integrations` to fetch the status of your active data pipelines. If a connection is failing, the agent detects the anomaly and can halt downstream reporting tasks.

All data processing occurs within an isolated, ephemeral V8 sandbox hosted by Vinkius. Your unified marketing performance data and channel lists are transmitted over encrypted TLS connections and are never cached, logged, or exposed to third parties.

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