How to Use the FunnelCockpit MCP in LangChain

Q: Can I create a LangChain agent to sync contacts between FunnelCockpit and another CRM?

Yes. Your agent can use listcontacts from FunnelCockpit and then call tools from another MCP server to create or update records there. You're building a bridge between systems, with your agent as the operator.

Q: What's the best way to start building with FunnelCockpit and LangChain?

Start simple. Build an agent that just uses listfunnels and prints the result. Then, have it take the ID from one funnel and pass it to getfunnel. This shows you the basic chain of execution.

Build autonomous marketing agents for FunnelCockpit with LangChain. Chain tool calls to create, update, and analyze your marketing data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FunnelCockpit MCP to LangChain

Create your Vinkius account to connect FunnelCockpit 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 FunnelCockpit with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Funnel and Contact Tools

Your LangChain agent can now run your entire marketing backend. It can start by calling `list_funnels` to find the right sales funnel, then use that ID to pull the specific details with `get_funnel`. From there, the agent can decide to `list_contacts` from a specific campaign or even create a new lead using `create_contact`. It's a sequence of decisions, all managed by your agent, not a static script.

Run Complex Marketing Pipelines

This isn't just about single API calls. You build agents that reason about your FunnelCockpit data. For example, an agent can `list_campaigns`, find one that's underperforming, and then create a new contact segment to test a new offer. Because LangChain treats each tool as a step in a chain, you can build complex logic. Your agent can `update_contact` records based on results from other tools, all within the same execution chain. This MCP Server connects your marketing data to the rest of your stack.

Debug LangChain Agents with Full Tracing

Every call your LangChain agent makes to the FunnelCockpit MCP server is fully observable. You can see the exact inputs for `create_contact` and the exact output from `get_contact` in your traces. This makes debugging complex chains simple. You'll know why your agent chose a specific funnel or why an `update_contact` call failed. No more black boxes.

Setup guide

Set up FunnelCockpit 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 FunnelCockpit 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({
    "funnelcockpit-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 FunnelCockpit 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 FunnelCockpit. 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 FunnelCockpit 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 FunnelCockpit MCP in LangChain

A script follows a fixed path. A LangChain agent uses the FunnelCockpit tools to decide its own path based on the data it finds. It might `list_funnels` and then decide to check `list_campaigns` next, all on its own.

Yes. Your agent can use `list_contacts` from FunnelCockpit and then call tools from another MCP server to create or update records there. You're building a bridge between systems, with your agent as the operator.

Start simple. Build an agent that just uses `list_funnels` and prints the result. Then, have it take the ID from one funnel and pass it to `get_funnel`. This shows you the basic chain of execution.

Absolutely. LangSmith traces will show you every tool call, including latency and the exact JSON passed to tools like `create_contact`. You get a full audit trail of your agent's interactions.

Your contact information is only passed through our ephemeral, zero-trust Vinkius sandbox during the API call. LangChain itself doesn't store your data, and we process the `create_contact` payload in memory without logging it.

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