How to Use the Google Ads MCP in LangChain

Q: Can I trace Google Ads tool calls made by LangChain in LangSmith?

Yes, every Google Ads tool execution like getadperformance shows up in your LangSmith dashboard automatically. You can inspect the exact input parameters, latency, and raw JSON returned from the Google Ads API within your LangChain pipeline.

Control your Google Ads budget and track keyword shifts directly inside your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Ads MCP to LangChain

Create your Vinkius account to connect Google Ads 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 Google Ads with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Google Ads API calls with LangChain

The `get_campaign_report` tool pulls raw Google Ads performance metrics that your LangChain agent feeds directly into downstream analysis chains. This setup lets you build multi-step LangChain reasoning loops where a drop in Google Ads CTR triggers a secondary search for better search terms. Your LangChain agent handles the logic, pulling Google Ads metrics and passing them to the next link without manual intervention. You trace every single Google Ads tool execution using LangSmith to spot latency spikes or weird token usage in your LangChain loops. When your LangChain agent calls `get_keyword_performance`, you see the exact input, the raw Google Ads API response, and how the LLM parsed it in LangSmith. This transparency keeps your automated Google Ads bidding chains from running wild or burning budget on bad queries.

Run ReAct loops to fix budget leaks

The `list_budgets` tool exposes your current Google Ads spending limits so your LangChain agent can make real-time allocation decisions. Instead of just reading data, the LangChain agent evaluates Google Ads performance and decides whether to shift funds to winning campaigns. It balances the Google Ads budget across accounts using a structured LangChain reasoning loop. By connecting this Google Ads MCP Server to your LangChain chains, you stop logging into the web UI just to check pacing. The LangChain agent monitors daily Google Ads limits and flags overspending before it ruins your margins. You get a self-correcting LangChain system that keeps your Google Ads acquisition costs where they belong.

Track keyword shifts dynamically

The `search_keywords` tool finds high-performing Google Ads search terms and feeds them directly into your LangChain vector store pipelines. Your LangChain agent compares these new Google Ads terms against existing ad groups to find gaps in your targeting. It executes this Google Ads search autonomously whenever overall LangChain campaign chain performance dips. You combine this Google Ads keyword tool with `get_change_status` to see if competitor moves caused your LangChain metrics to drop. The LangChain agent processes these Google Ads status changes, updates its internal context, and suggests immediate bid adjustments. It turns raw Google Ads search data into immediate tactical updates for your LangChain marketing pipelines.

Setup guide

Set up Google Ads 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 Google Ads 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({
    "google-ads-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 Google Ads 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 Google Ads. 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 Google Ads 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 Google Ads MCP in LangChain

You pass your single Vinkius token to the LangChain MultiServerMCPClient during initialization. The server manages the Google Ads OAuth developer token handshake behind the scenes, so your LangChain agent never handles raw Google Ads API credentials directly.

Yes, every Google Ads tool execution like `get_ad_performance` shows up in your LangSmith dashboard automatically. You can inspect the exact input parameters, latency, and raw JSON returned from the Google Ads API within your LangChain pipeline.

You limit the LangChain agent's tools to read-only Google Ads endpoints like `get_campaign_details` and `get_keyword_performance`. This restriction ensures the LangChain agent only analyzes performance without any permission to modify your actual Google Ads campaign budgets.

Yes, you can register this Google Ads server alongside your database tools in a single LangChain MultiServerMCPClient instance. Your LangChain agent can then query Google Ads data and cross-reference it with your internal sales database in one turn.

All Google Ads campaign performance metrics and budget caps processed by this MCP Server remain inside an ephemeral V8 sandbox. Vinkius never stores your retrieved Google Ads reports on persistent disks, keeping your marketing data isolated from other LangChain operations.

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