How to Use the Kevel MCP in LangChain

Q: How do I connect the Kevel MCP server to LangChain?

Install langchain-mcp-adapters and langgraph. Then initialize a MultiServerMCPClient pointing to your Vinkius endpoint URL. Call client.gettools() and pass the resulting array directly into your agent constructor.

Build ad operations chains by connecting the Kevel MCP server directly to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to LangChain

Create your Vinkius account to connect Kevel 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 Kevel with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate ad ops workflows in LangChain

You build ad-tech pipelines by stringing together API calls. LangChain agents can now query your Kevel management environment to audit active inventory. They pull active placements using `list_zones` and `list_sites`, then map those directly to available creative assets. The agent decides the sequence. If a user asks for campaign status, the chain triggers `list_campaigns` to find the ID, followed by `get_campaign` for the deep dive. Every step gets logged in LangSmith so you can track token usage and API latency across the entire MCP Server execution.

Audit ad structures autonomously

Ad ops teams spend hours hunting down mismatched creatives and flights. You can fix that by wiring up a ReAct agent to scan your setup. The agent pulls everything via `list_flights` and `list_ads` to check for targeting conflicts or missing assets. It feeds those results right back into your workflow. Because this is a read-only integration, your agent can safely map out the entire ad taxonomy using `list_ad_types` and `list_channels` without risking accidental changes to production delivery.

Connect campaign data to external tools

Kevel data rarely lives in a vacuum. Your agent can grab advertiser details using `get_advertiser` and immediately cross-reference them with your CRM or billing databases. The output of one tool call becomes the exact input for the next step in your chain. This eliminates manual copy-pasting between dashboards. When sales reps need an inventory forecast, the agent pulls active `list_creatives` and formats a complete report before sending it to Slack.

Setup guide

Set up Kevel 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 Kevel 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({
    "kevel-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 Kevel 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 Kevel. 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 Kevel 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 Kevel MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph`. Then initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint URL. Call `client.get_tools()` and pass the resulting array directly into your agent constructor.

No. The current toolset is strictly read-only. Your agents can run `list_campaigns` or `get_campaign`, but they cannot create or update ad delivery rules.

You get full observability and composability. When an agent chains a `list_advertisers` call into a database lookup, LangSmith traces the exact inputs, outputs, and latency for every step.

Yes. You can aggregate this ad management server with other tools. Your agent can pull inventory data from Kevel and immediately pass it to a separate server handling Slack or Jira notifications.

Your agent reads sensitive advertiser details, campaign budgets, and creative URLs directly from your ad engine. The Vinkius V8 Isolate Sandbox ensures this execution environment is ephemeral. Tokens are destroyed immediately after the session, keeping your proprietary ad network data isolated from outside access.

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