How to Use the Leadfeeder MCP in LangChain

Q: How do I connect the Leadfeeder MCP Server to my LangChain agent?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with your Vinkius endpoint. Call client.gettools() to fetch the 9 Leadfeeder tools and pass them directly to your agent constructor.

Q: Can I use custom feeds to filter leads in LangChain?

Yes. You run listcustomfeeds to fetch your pre-defined filters, then pass the feed ID to getcustomfeed to pull only highly targeted company visits.

Feed real-time anonymous B2B website visit data straight into 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 Leadfeeder MCP to LangChain

Create your Vinkius account to connect Leadfeeder 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 Leadfeeder with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step routing chains with LangChain

`list_leads` pulls the raw list of companies hitting your site and hands them off to the next link in your run. Your agent looks at who visited, decides if they match your ideal profile, and immediately routes the high-value accounts to your sales reps. If the account looks promising, the chain automatically triggers `list_lead_visits` to check exactly which pages they viewed. This keeps your sales outreach highly relevant without manual research.

Track Leadfeeder MCP Server calls in LangSmith

`list_custom_feeds` identifies specific customer segments directly inside your active pipeline. By executing this through an MCP Server, every call, latency metric, and token count shows up inside your LangSmith dashboard. You see exactly when your chains query `get_lead` to pull firmographic details. Debugging failing lead-routing logic takes seconds because you can trace the exact payload passed between tools.

Feed firmographic data into agent prompts

`get_account` retrieves the metadata needed to personalize your outbound sales sequences. Your LangChain agent grabs this data dynamically, injecting company size and industry into your draft emails. Using `get_custom_feed` lets the agent filter out low-intent traffic before generating these drafts. You only spend tokens on companies that actually spend time reading your high-value pages.

Setup guide

Set up Leadfeeder 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 Leadfeeder 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({
    "leadfeeder-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 Leadfeeder 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 Leadfeeder. 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 Leadfeeder 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 Leadfeeder MCP in LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with your Vinkius endpoint. Call `client.get_tools()` to fetch the 9 Leadfeeder tools and pass them directly to your agent constructor.

Yes, you can chain these tools sequentially. For example, your agent can run `list_leads` first, filter the results, and then immediately call `get_lead` for the most promising matches.

Use LangSmith to trace every single tool execution. You will see the exact latency for tools like `list_account_visits` and can pinpoint if the delay is from the API or your chain's decision logic.

Yes. You run `list_custom_feeds` to fetch your pre-defined filters, then pass the feed ID to `get_custom_feed` to pull only highly targeted company visits.

The server only processes corporate IP visits and firmographic metadata, completely ignoring personal consumer data. Vinkius runs the code in secure, ephemeral V8 sandboxes so your API tokens and company traffic records never persist on disk.

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