How to Use the AdRoll MCP in LangChain

Q: How do I connect the AdRoll MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph. You pass the Vinkius endpoint URL to MultiServerMCPClient and call gettools() to bind them to your ReAct agent.

Q: Can LangChain agents read AdRoll performance reports?

Yes. The agent calls getperformancereport with your specified EID and date range. It parses the returned JSON to calculate cost per click or overall return on ad spend.

Build multi-step ReAct agents in LangChain that pull AdRoll performance data and adjust e-commerce campaigns automatically via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to LangChain

Create your Vinkius account to connect AdRoll 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 AdRoll with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain AdRoll MCP Server Tool Calls

`get_performance_report` feeds raw statistics directly into your LangChain reasoning pipeline. Your agent checks the return on ad spend for a specific EID and date range. The output immediately becomes the input for the next node in your graph. You build a sequence where the agent pulls metrics, evaluates the cost per acquisition against your target margin, and decides if it needs to pull more data.

Trace Marketing Logic via LangSmith

`list_campaigns` grabs your active e-commerce retargeting efforts so your agent can inspect them. You see exactly what context the LLM received and how many tokens it burned to process those campaign lists. Full observability matters when money is on the line. If an agent misinterprets an ad group's status, you check the LangSmith trace to fix the prompt or adjust the tool parameters.

Retrieve Campaign Metadata

`get_campaign_details` pulls the underlying configuration for any active marketing push. The agent reads budget caps, targeting parameters, and schedule constraints. `list_ads` then fetches the actual creatives tied to that campaign. Your script correlates the specific banner variations with the performance metrics to figure out which visual drives the most clicks.

Setup guide

Set up AdRoll 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 AdRoll 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({
    "adroll-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 AdRoll 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 AdRoll. 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 AdRoll 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 AdRoll MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. You pass the Vinkius endpoint URL to `MultiServerMCPClient` and call `get_tools()` to bind them to your ReAct agent.

Yes. The agent calls `get_performance_report` with your specified EID and date range. It parses the returned JSON to calculate cost per click or overall return on ad spend.

That is exactly how you build this. A chain might start by running `list_advertisables` to find the account ID, then pass that ID down to fetch campaigns and ads in sequence.

The tool returns the error string to the LLM. Your agent reads the failure reason and can try again with different parameters or halt the execution entirely.

Your ad creatives, budgets, and performance statistics run through a V8 Isolate Sandbox. The Vinkius endpoint requires a single token to authenticate, and the ephemeral session destroys all memory of your e-commerce metrics the moment the connection closes.

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