How to Use the Cometly MCP in LangChain

Q: How do I pass Cometly campaign data between steps in a LangChain run?

You use the output of getcampaignstats as the direct input for your next chain link. LangChain handles the state, letting your agent read the performance metrics and immediately decide whether to trigger a new event or alert.

Q: Can I trace Cometly tool execution latency using LangChain and LangSmith?

Yes. Every call to listadaccounts or trackevent shows up inside your LangSmith dashboard. You can inspect the exact payload sent to Cometly, see how long the API took to respond, and debug any failed attribution calls.

Q: How do I initialize the Cometly MCP Server inside a LangChain agent?

Install the adapter package and use MultiServerMCPClient pointing to your Vinkius endpoint. Call gettools() to fetch the Cometly utilities and pass them directly to your agent constructor to start tracking conversions.

Q: Can my LangChain agent automatically flag failing Meta or Google campaigns?

Yes. Your agent can run a scheduled loop that calls listcampaigns followed by getcampaignstats. If the ROAS drops below your threshold, the chain triggers an alert with the exact campaign details.

Feed real-time ad attribution and campaign performance directly into your LangChain multi-step 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 Cometly MCP to LangChain

Create your Vinkius account to connect Cometly 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 Cometly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route LangChain agents using live Cometly attribution

Using `list_contacts` allows your LangChain agent to inspect actual customer journeys before deciding the next step in your email sequence. It doesn't guess, but instead reads the touchpoints and branches your chain accordingly. If a contact shows high-intent touchpoints, the chain automatically triggers `track_purchase` to log the conversion. You can monitor this entire execution flow inside LangSmith to see exactly how your agent parsed the journey data before firing the event.

Build self-correcting ad budget loops in LangChain

Your LangChain agent queries `list_campaigns` to find active runs, then passes those IDs directly into `get_campaign_stats` to analyze ROI. This sequential handoff happens in a single execution chain without manual code. When stats fall below your target threshold, the chain flags the underperforming ad account found via `list_ad_accounts`. Since LangChain handles complex multi-step reasoning, your agent can draft Slack alerts or queue budget adjustments based on these live metrics.

Feed instant conversions back to this MCP Server

Calling `track_event` or `track_lead` pushes conversion signals to Cometly the second they happen in your LangChain pipeline. This keeps your attribution models fresh without waiting for nightly batch uploads. Because LangChain supports multi-server aggregation, you can combine this MCP tool with your database connectors. The agent pulls a new sign-up from PostgreSQL and instantly registers it as a lead in Cometly within the same logical chain.

Setup guide

Set up Cometly 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 Cometly 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({
    "cometly-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 Cometly 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 Cometly. 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 Cometly 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 Cometly MCP in LangChain

You use the output of `get_campaign_stats` as the direct input for your next chain link. LangChain handles the state, letting your agent read the performance metrics and immediately decide whether to trigger a new event or alert.

Yes. Every call to `list_ad_accounts` or `track_event` shows up inside your LangSmith dashboard. You can inspect the exact payload sent to Cometly, see how long the API took to respond, and debug any failed attribution calls.

Install the adapter package and use `MultiServerMCPClient` pointing to your Vinkius endpoint. Call `get_tools()` to fetch the Cometly utilities and pass them directly to your agent constructor to start tracking conversions.

Yes. Your agent can run a scheduled loop that calls `list_campaigns` followed by `get_campaign_stats`. If the ROAS drops below your threshold, the chain triggers an alert with the exact campaign details.

Vinkius runs the MCP Server in an isolated V8 sandbox that never stores your credentials or contact details. When your agent queries `list_contacts` or `list_ad_accounts`, the data passes through in-memory and vanishes as soon as the execution finishes.

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