How to Use the Leadfeeder MCP in AutoGen

Q: How do I register Leadfeeder tools with my AutoGen agents?

Install autogen-extmcp and use mcpservertools with your Vinkius endpoint. Pass the resulting tool list to your AssistantAgent to let them execute the API calls during their conversation.

Q: Can AutoGen agents share Leadfeeder data during a debate?

Yes. When one agent calls getlead, the firmographic output is written to the shared conversation history, allowing all other agents in the group to read and analyze the company details.

Q: Can I use AutoGen to automatically deploy the Leadfeeder tracking script?

Your agent can call gettrackingscript to fetch the JavaScript snippet. From there, you can route that script output to a file-writing agent or a deployment pipeline to add it to your site.

Let your AutoGen agents debate and qualify high-intent B2B leads using real-time website visit metrics.

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 AutoGen

Create your Vinkius account to connect Leadfeeder to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Qualify leads via AutoGen agent consensus

`list_leads` serves as the starting point for your multi-agent sales qualification workflow. One agent pulls the raw visitor list, while a second agent analyzes the company profiles to flag target accounts. They debate whether the visitor matches your buying persona. By forcing a consensus before writing to your CRM, you stop junk traffic from cluttering your sales pipeline.

Analyze intent with the Leadfeeder MCP Server

`list_lead_visits` provides the exact page-by-page path a company took through your website. Your AutoGen research agent analyzes this path to estimate their buying stage. A separate outbound agent uses this analysis to draft targeted emails. The two agents negotiate the best messaging based on which specific product pages the prospect read.

Filter accounts using AutoGen conversations

`list_custom_feeds` retrieves your pre-configured target lists, like companies with active funding or specific industries. Your coordinator agent uses these feeds to assign leads to specialized sales agents. The assigned agent then calls `get_custom_feed` to drill into the specific behavior of those leads. This keeps your agents focused on high-value accounts instead of processing raw traffic.

Setup guide

Set up Leadfeeder MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Leadfeeder tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Leadfeeder_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Leadfeeder data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Leadfeeder_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Leadfeeder data")
    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 AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius endpoint. Pass the resulting tool list to your `AssistantAgent` to let them execute the API calls during their conversation.

Yes. When one agent calls `get_lead`, the firmographic output is written to the shared conversation history, allowing all other agents in the group to read and analyze the company details.

The Vinkius runtime handles the connection stability, but you should instruct your manager agent to space out calls to `list_account_visits` to avoid hitting API rate limits during intense debates.

Your agent can call `get_tracking_script` to fetch the JavaScript snippet. From there, you can route that script output to a file-writing agent or a deployment pipeline to add it to your site.

The server runtimes on Vinkius use isolated V8 sandboxes that execute the code in memory. Your account details and company visitor lists are never stored or shared with other tenants.

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