How to Use the Adjust MCP in Pydantic AI

Q: How do I use the Adjust tools with Pydantic AI?

You'll import MCPToolset from the Pydantic AI library and initialize it with your Vinkius server URL. Then, you pass it in the toolsets list when you create your Agent. The framework handles the rest.

Get type-safe, validated Adjust data directly in your Pydantic AI agent. No more silent data corruption from API changes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adjust MCP to Pydantic AI

Create your Vinkius account to connect Adjust 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 Adjust with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe KPI Reports

The `get_kpi_report` tool fetches your mobile marketing KPIs from Adjust. Your agent requests a report, and the MCP server returns the data. Here's the Pydantic AI difference: the response is automatically parsed and validated against a Pydantic model. If Adjust ever adds a field or changes a data type unexpectedly, your code will raise a `ValidationError` immediately. You'll never process bad data by accident.

Reliably Inspect Device Attribution

Use the `inspect_device` tool to have your agent look up attribution data for a single device. It's a key function for building support bots or fraud detection systems. With Pydantic AI, you define the exact structure you expect for device data. If the server returns anything else—a missing field, a null value where you expect a string—your agent stops. This focus on correctness is critical when you're making decisions based on attribution data.

Build Correctness-First Agents with this MCP Server

This MCP Server provides simple tools like `get_app_settings` for checking your configuration. It's a straightforward way to build automated checks into your marketing operations. Pydantic AI makes these checks bulletproof. You aren't just calling an endpoint; you're calling a function that guarantees the output matches a specific data contract. This lets you build reliable agents that work with any LLM, from OpenAI to a local model.

Setup guide

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

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

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

You'll import `MCPToolset` from the Pydantic AI library and initialize it with your Vinkius server URL. Then, you pass it in the `toolsets` list when you create your `Agent`. The framework handles the rest.

Runtime validation. Every response from the Adjust server is parsed into a Pydantic model. If the data doesn't match the model's schema exactly, Pydantic AI throws an error, preventing your agent from working with corrupted or unexpected data.

Yes, it's model-agnostic. You can use this Adjust MCP server with Pydantic AI whether you're using OpenAI, Anthropic, Gemini, or a local model. The tool-use logic is separate from the LLM provider.

It fails loudly and explicitly. If the Adjust server returns data that doesn't fit the expected Pydantic model for a tool like `get_kpi_report`, you'll get a `ValidationError`. This is a feature, not a bug—it protects your system from silent failures.

The server only exposes tools for specific Adjust data: app settings, KPI metrics, and device attribution details. Pydantic AI calls your Vinkius endpoint, which proxies the request to Adjust in a zero-trust, ephemeral environment. Your data isn't logged or stored by the Vinkius MCP server.

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