How to Use the Criteo Retail Media API MCP in LangChain

Q: Can LangChain trace calls made to the Criteo Retail Media API?

Yes, every call to getretailmediareport or listlineitems shows up in your LangSmith dashboard. You can inspect the exact inputs, outputs, and latency of each Criteo tool call.

Run multi-step retail ad optimization chains in LangChain using direct Criteo data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Criteo Retail Media API MCP to LangChain

Create your Vinkius account to connect Criteo Retail Media API to LangChain 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 Criteo Retail Media API with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated budget checks in LangChain pipelines

Your LangChain agent can pull active budgets with this MCP Server using `list_retail_budgets` and feed those numbers directly into your next chain step. Your pipeline can automatically branch based on remaining spend, deciding whether to pull deeper metrics or pause. Instead of manual lookups, the output of `list_retail_campaigns` flows straight into `list_line_items` to map your entire retail ad structure in a single run. LangSmith traces every step so you see exactly how the agent moves from budget data to campaign details.

Targeted keyword expansion with LangChain chains

The Criteo Retail Media API provides raw keyword targeting data that your LangChain agent can analyze and expand on the fly. By calling `list_line_item_keywords`, your agent inspects current targets and compares them against your product library. You can chain this keyword list with `list_account_products` to find gaps where active SKUs lack search coverage. The agent runs these lookups sequentially, building a prompt with real-time inventory and search terms.

Performance reporting via LangChain ReAct agents

This toolset lets your LangChain ReAct agent request and parse performance data using `get_retail_media_report`. The agent evaluates the report and chooses its next action based on actual conversion metrics. If conversion drops, the agent can search for trouble spots by triggering `search_retail_campaigns_by_name` or checking specific retailer setups with `list_retailers`. You get a self-correcting loop that reacts to real-time ad performance without human intervention.

Setup guide

Set up Criteo Retail Media API MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Criteo Retail Media API tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "criteo-retail-media-api-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Criteo Retail Media API transactions"
    })
    print(result["messages"][-1].content)

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 Criteo Retail Media. 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 Criteo Retail Media API 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 Criteo Retail Media API MCP in LangChain

You use the LangChain MCP adapter to convert the server tools into standard LangChain tools. Just call `client.get_tools()` and pass them to your agent constructor to let it run campaigns.

Yes, every call to `get_retail_media_report` or `list_line_items` shows up in your LangSmith dashboard. You can inspect the exact inputs, outputs, and latency of each Criteo tool call.

The LangChain agent uses a ReAct loop to decide which tool to call next. For example, it might list accounts with `list_advertiser_accounts` first, then use that ID to pull campaigns.

Yes. The MultiServerMCPClient aggregates this server with others, allowing your agent to combine Criteo data with inventory databases in one chain.

Your Criteo advertiser account listings and campaign budgets are processed inside Vinkius's secure, ephemeral sandbox. No raw credentials or retail performance data are stored on our servers or exposed to external networks.

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