How to Use the Follow Up Boss MCP in AutoGen

Q: How do I give my AutoGen agents access to Follow Up Boss?

You use the mcpservertools function from the AutoGen extension, pointing it to your MCP server endpoint. This function fetches all available Follow Up Boss tools and makes them usable by any agent in your multi-agent conversation. The McpToolAdapter handles all the schema conversions automatically.

Deploy teams of AI agents to manage Follow Up Boss with AutoGen. Let them debate the best course of action for every lead and task.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Follow Up Boss MCP to AutoGen

Create your Vinkius account to connect Follow Up Boss 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 Follow Up Boss with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Lead Strategy

With AutoGen, you set up multiple agents that talk to each other. A 'Scout' agent can use `list_smart_lists` to find new, high-value leads. Instead of acting alone, it presents the lead to a 'Strategist' agent. The Strategist can then use `list_events` to check the lead's website activity and debate the best first touchpoint. This conversational approach means you're not locked into a single, rigid workflow. The agents can reason together, challenge assumptions, and arrive at a better plan. One agent might propose an immediate call, while another argues for a personalized email first, based on the data.

Create Specialist Agent Teams

Build a team of agents with specific roles. You can have a 'Taskmaster' agent whose only job is to run `list_tasks` and find overdue items. When it finds one, it doesn't just send a generic alert. It passes the task details to a 'Communicator' agent. The Communicator then uses `get_person` to pull the contact's name and `get_deal` to find the associated deal value. It formulates a specific, context-rich prompt for the human agent and logs it using `add_note`. The final action is a result of their collaboration.

Simulate Your Sales Team with an AutoGen MCP Server

Model your real estate team's decision-making process. You can configure one `AssistantAgent` to act as your data-driven ops manager and another to act as your aggressive top salesperson. Then, you can feed them the output of `list_deals` from the Follow Up Boss MCP server. Watch them converse about the data. The ops agent might argue for focusing on nurturing older leads, while the sales agent pushes to prioritize new ones. It’s a powerful way to explore strategies and pressure-test your ideas before committing your human team's time.

Setup guide

Set up Follow Up Boss 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 Follow Up Boss 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="Follow Up Boss_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Follow Up Boss 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="Follow Up Boss_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Follow Up Boss 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 Follow Up Boss. 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 Follow Up Boss 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 Follow Up Boss MCP in AutoGen

You use the `mcp_server_tools` function from the AutoGen extension, pointing it to your MCP server endpoint. This function fetches all available Follow Up Boss tools and makes them usable by any agent in your multi-agent conversation. The `McpToolAdapter` handles all the schema conversions automatically.

Yes. When you define each agent, you can provide a specific list of functions it's allowed to call. For example, your 'Auditor' agent might only have access to read-only tools like `list_people` and `get_deal`, while your 'Executor' agent has permission to use write tools like `create_task`.

A user proxy might ask, "Find any hot leads we haven't contacted." One agent could use `list_smart_lists` and pass the results to another. That second agent might then use `list_person_notes` on each lead, and reply, "Lead X has no notes, I suggest we call them." The action is the result of a discussion.

AutoGen agents connect to the Vinkius-managed MCP server via an HTTP transport. Your agents run in your environment, and they make secure calls to the server endpoint, which then interacts with the Follow Up Boss API. You don't need to host the tool server yourself.

Your Follow Up Boss data, like people records and deal information, is handled within your AutoGen environment. The MCP server provides the secure connection, but the agent conversations and any data they handle are processed in your infrastructure. You have full control over the conversation logs and where data from tool calls is stored.

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