How do I get my Adikteev API account?

You must contact your Adikteev Account Manager to have them enable API access for your account. Once enabled, you can use your standard login credentials (email and password) to authorize the agent.

What is a Churn Score?

A churn score ranks app users by their probability of leaving. Adikteev provides these in 'buckets' from 1 to 10, where 10 represents the highest risk of churn.

How do I create a new audience segment?

Use the `create_segment` tool and provide your `companyId`, a name, and a description. Your agent will create the segment in Adikteev and provide a `segmentId` for device ID uploads.

Adikteev MCP Server for Pydantic AI 5 tools — connect in under 2 minutes

Name: Adikteev
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 5 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Adikteev 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 Adikteev "
            "(5 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Adikteev?"
    )
    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 Adikteev MCP Server

Connect your Adikteev account to your AI agent to unlock professional app retargeting and user retention insights. From managing custom audience segments to monitoring campaign performance and retrieving churn probability scores, your agent handles your mobile growth ecosystem through natural conversation.

Pydantic AI validates every Adikteev tool response against typed schemas, catching data inconsistencies at build time. Connect 5 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

Audience Orchestration — List, create, and manage audience segments for targeted app retargeting campaigns
Performance Reporting — Retrieve detailed campaign performance data to monitor ROI and engagement metrics
Churn Prediction — Access churn probability scores to identify at-risk app users before they leave your ecosystem
Company Insights — List companies and retrieve technical metadata required for audience management
Growth Monitoring — Quickly audit your retargeting efforts and identify high-value user segments directly from chat

The Adikteev MCP Server exposes 5 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 Adikteev to Pydantic AI via MCP

Follow these steps to integrate the Adikteev 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 5 tools from Adikteev with type-safe schemas

Why Use Pydantic AI with the Adikteev MCP Server

Pydantic AI provides unique advantages when paired with Adikteev 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 Adikteev integration code

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

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

Adikteev + Pydantic AI Use Cases

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

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

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

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

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

Adikteev MCP Tools for Pydantic AI (5)

These 5 tools become available when you connect Adikteev to Pydantic AI via MCP:

create_segment

Create an audience segment

get_churn_scores

Retrieve user churn scores

get_reporting

Get campaign performance data

list_companies

Retrieve your company ID

list_segments

List audience segments

Example Prompts for Adikteev in Pydantic AI

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

"List all audience segments for my company."

"Retrieve the churn scores for my app with bundle 'com.example.app'."

"Show me the performance of my retargeting campaigns."

Troubleshooting Adikteev MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Adikteev + Pydantic AI FAQ

Common questions about integrating Adikteev 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 Adikteev MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.