How do I get Criteo API credentials?

Log in to the Criteo Developer Portal, create a new app, and you will be provided with a Client ID and Client Secret.

Which version of the API is used?

This integration uses the 2024-04 version of the Criteo Marketing API, ensuring access to the latest features and data structures.

Can I retrieve reporting data?

Yes, you can use the get_marketing_statistics tool to retrieve performance reports based on custom dimensions and metrics.

Criteo Marketing API MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Criteo Marketing API
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 Criteo Marketing API 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 Criteo Marketing API "
            "(10 tools)."
        ),
    )

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

Integrate the Criteo Marketing API directly into your AI workflow. Manage your commerce marketing campaigns, monitor ad set performance, and track budgets and creatives across your advertiser accounts using natural language.

Pydantic AI validates every Criteo Marketing API 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

Campaign Management — List and retrieve detailed settings for all your marketing campaigns.
Performance Monitoring — Access real-time statistics and analytics for your ad sets and creatives.
Budget Tracking — Monitor active budgets and spend across your advertiser portfolio.
Audience Insights — Explore target audiences and available audience segments via chat.

The Criteo Marketing API 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 Criteo Marketing API to Pydantic AI via MCP

Follow these steps to integrate the Criteo Marketing API 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 Criteo Marketing API with type-safe schemas

Why Use Pydantic AI with the Criteo Marketing API MCP Server

Pydantic AI provides unique advantages when paired with Criteo Marketing API 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 Criteo Marketing API integration code

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

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

Criteo Marketing API + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Criteo Marketing API MCP Server delivers measurable value.

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

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

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

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

Criteo Marketing API MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Criteo Marketing API to Pydantic AI via MCP:

get_ad_set_details

Get detailed configuration for an ad set

get_campaign_details

Get detailed settings for a specific campaign

get_marketing_statistics

Retrieve performance statistics for campaigns or ad sets

list_ad_creatives

List all ad creatives (banners, videos, etc.)

list_ad_sets

List all ad sets (groups) within campaigns

list_advertisers

List advertisers managed in your account

list_audience_segments

List available audience segments

list_audiences

List target audiences for your campaigns

list_marketing_budgets

List active budgets and their spend

list_marketing_campaigns

List all marketing campaigns in Criteo

Example Prompts for Criteo Marketing API in Pydantic AI

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

"List all active marketing campaigns in my Criteo account."

"Show me the performance statistics for ad set 's8s9df7' from last week."

"List all target audiences available for my advertisers."

Troubleshooting Criteo Marketing API MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Criteo Marketing API + Pydantic AI FAQ

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