How to Use the Follow Up Boss MCP in LangChain

Q: Can I use this to manage team tasks in Follow Up Boss with LangChain?

Definitely. You can build an agent that periodically runs listtasks to find everything assigned to a specific user. It can then summarize those tasks, check their due dates, and send a digest to that user via a different tool, like a messaging service.

Build lead management pipelines for Follow Up Boss with LangChain. Connect tools to automate your entire sales process from start to finish.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Lead Intake to Task Creation

This isn't just about single commands. You build chains of action. When a new lead hits your website, your LangChain agent can immediately use `create_person` to add them to Follow Up Boss, then check against `list_crm_users` and instantly `create_task` for the right agent. Because it's a single, unbroken chain, nothing gets dropped. You define the logic for routing and follow-up once, and your agent executes it every time. It's how you guarantee speed-to-lead without manual work.

Build Autonomous Deal Watchdogs

Create an agent that runs on a schedule to monitor your pipeline's health. It starts by using `list_deals` to pull all open opportunities, filtering for any that haven't been touched in the last three days. It's your automated accountability partner. For each stalled deal it finds, the agent can dig deeper with `get_deal` and `list_person_notes` to understand the context. Based on your rules, it can then `add_note` with a pointed reminder for the assigned agent, keeping everything moving.

Fully Observable LangChain Pipelines

Every call your agent makes to the Follow Up Boss MCP Server is traced and visualized in LangSmith. You get a clear, step-by-step view of the agent's reasoning and actions. See the exact inputs for a `get_person` call, check the raw output, and measure the latency of every tool use. This isn't a black box. If an agent isn't behaving as expected, you can pinpoint the exact step in the chain that failed. Debugging complex workflows that interact with your CRM data becomes straightforward, not a guessing game.

Setup guide

Set up Follow Up Boss 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 Follow Up Boss 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({
    "follow-up-boss-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 Follow Up Boss 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 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 LangChain

First, install the Vinkius adapter for LangChain. Then, you'll instantiate the client with your server endpoint token and call `get_tools()`. The tools returned are ready to be passed directly into your agent executor, letting it work with your Follow Up Boss MCP server right away.

Yes, that's what it's built for. You can create a chain where your agent first calls `get_person` from the Follow Up Boss MCP server, then uses that information to query a separate database or API. LangChain is designed to orchestrate tool use across different services.

LangChain agents can be designed with error handling logic. You can build your chains to catch exceptions from tool calls, like an API timeout, and then retry the action or trigger a different fallback tool. This makes your automations more resilient.

Definitely. You can build an agent that periodically runs `list_tasks` to find everything assigned to a specific user. It can then summarize those tasks, check their due dates, and send a digest to that user via a different tool, like a messaging service.

Your LangChain agent accesses only the Follow Up Boss data you permit, like contacts, deals, and tasks. Since LangChain is a framework you run yourself, that data is processed within your own environment. This MCP server simply provides a secure, encrypted transport layer between your agent and the Follow Up Boss API.

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