How to Use the Adikteev MCP in Pydantic AI

Q: How do I integrate Adikteev with Pydantic AI?

Install pydantic-ai-slimmcp via pip. Initialize an MCPToolset with your Vinkius HTTP endpoint and pass it into your Agent's toolsets list. Do not use the deprecated MCPServerHTTP class.

Force strict type validation on your Adikteev campaigns using Pydantic AI to ensure agents never hallucinate retargeting data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to Pydantic AI

Create your Vinkius account to connect Adikteev 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 Adikteev with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe churn analysis

When your agent calls `get_churn_scores` through the MCP Server, Pydantic AI validates the exact structure of the returned JSON. If the API drops a field or changes a type, the framework throws a loud validation error immediately. This strictness guarantees your agent always works with real, verified risk metrics. You can swap between OpenAI, Anthropic, or local models without worrying that a different LLM will misinterpret the churn probability numbers.

Flawless campaign reporting

Your agent executes `get_reporting` to pull down ad spend and conversion rates. Pydantic AI ensures every float and integer matches your expected schema before the agent attempts to summarize the performance for your marketing dashboard. If the agent needs to pull stats for a specific sub-account, it runs `list_companies` first. The framework guarantees the returned company ID is formatted correctly before passing it into the reporting query.

Build segments without errors

By exposing `create_segment` via MCP, your agent can generate new retargeting groups based on verified logic. Pydantic catches any malformed requests before they hit the external API, preventing bad data from corrupting your campaigns. To prevent duplicate work, the agent can also trigger `list_segments` to check what's already running. You get complete confidence that your audience management system is operating strictly within the bounds of reality.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp] via pip. Initialize an MCPToolset with your Vinkius HTTP endpoint and pass it into your Agent's toolsets list. Do not use the deprecated MCPServerHTTP class.

Yes. Every response from tools like the reporting fetcher runs through Pydantic models at runtime. If the payload structure differs from the schema, the execution halts with a clear error.

The framework is completely model-agnostic. You can point your setup at a local LLM, and it will still interact with the segment creation tools using the same strict validation rules.

The validation layer intercepts the request. The framework rejects the malformed call before it ever leaves your machine, preventing bad records from cluttering your account.

Vinkius handles authentication via a single endpoint token while keeping your execution environment ephemeral. When you pull ad spend and campaign performance data, the underlying sandbox processes the request and instantly terminates.

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