How to Use the LinkedIn Ads MCP in LangChain

Q: How does LangSmith trace LinkedIn Ads tool calls?

Every time your LangChain agent invokes listadcreatives or getadanalytics, LangSmith logs the exact inputs, outputs, and latency. You see exactly what data the server returned and how the agent used it.

Feed live LinkedIn Ads metrics directly into your LangChain multi-step reasoning chains with a single secure endpoint.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LinkedIn Ads MCP to LangChain

Create your Vinkius account to connect LinkedIn 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 LinkedIn Ads with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated attribution mapping with LangChain

Your LangChain agent can now use this MCP Server to query `get_ad_analytics` to pull performance metrics and instantly pass them to your attribution models. It doesn't just pull numbers; it uses the output of one step to decide which conversion rule to check next. By linking `list_conversion_rules` with your database chains, your LangChain agent spots discrepancies between LinkedIn reported conversions and your actual database records. This stops budget wastage on LinkedIn before your daily sync even runs.

Deep campaign discovery in your pipelines

Stop hardcoding account IDs into your LangChain pipelines. Your agent can run `list_ad_accounts` and `list_campaign_groups` dynamically to map out your entire LinkedIn Ads structure on the fly. This dynamic mapping feeds directly into downstream LangChain tools, allowing your pipeline to inspect `list_ad_campaigns` and flag paused campaigns that are still consuming budget.

Creative audits via ReAct agents

Let your LangChain ReAct agent fetch live creative assets using `list_ad_creatives` to analyze copy performance. It compares historical click rates with the actual text layout to recommend changes. The agent chains these creative insights with `get_ad_analytics` to build a feedback loop via this MCP tool that pauses low-performing creatives and drafts new copy variations.

Setup guide

Set up LinkedIn 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 LinkedIn 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({
    "linkedin-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 LinkedIn 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 LinkedIn 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 LinkedIn 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 LinkedIn Ads MCP in LangChain

Use MultiServerMCPClient to connect this MCP server, then grab the tools with client.get_tools() and pass them to your create_agent call. Your LangChain agent will automatically decide when to run `get_ad_analytics` based on the user's prompt.

Yes, the Vinkius infrastructure manages the underlying API connection, but you should also use LangChain's built-in retry logic when your agent runs loops over `list_ad_campaigns` to avoid hitting LinkedIn rate limits.

Every time your LangChain agent invokes `list_ad_creatives` or `get_ad_analytics`, LangSmith logs the exact inputs, outputs, and latency. You see exactly what data the server returned and how the agent used it.

Yes. You can register this server alongside your CRM tools in a single MultiServerMCPClient. The LangChain agent can pull spend from LinkedIn and correlate it with customer lifetime value in your database.

Vinkius runs the server in an ephemeral V8 sandbox, meaning your raw credentials never touch the client side. Only the final, filtered results from endpoints like `list_ad_accounts` are passed back to your LangChain environment.

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