How to integrate Follow Up Boss MCP with LlamaIndex

Framework Integration Gradient
Follow Up Boss Logo
LlamaIndex Logo
divider

Introduction

This guide walks you through connecting Follow Up Boss to LlamaIndex using the Composio tool router. By the end, you'll have a working Follow Up Boss agent that can list all leads added this week, update contact info for lead john doe, create a new deal for jane smith through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Follow Up Boss account through Composio's Follow Up Boss MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Follow Up Boss
  • Connect LlamaIndex to the Follow Up Boss MCP server
  • Build a Follow Up Boss-powered agent using LlamaIndex
  • Interact with Follow Up Boss through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

What is the Follow Up Boss MCP server, and what's possible with it?

The Follow Up Boss MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Follow Up Boss account. It provides structured and secure access so your agent can perform Follow Up Boss operations on your behalf.

Supported Tools & Triggers

Tools
Apply Action Plan to PersonTool to apply an Action Plan to a person in Follow Up Boss.
Create AppointmentTool to create a new appointment in Follow Up Boss.
Create appointment outcomeTool to create an appointment outcome in Follow Up Boss.
Create Appointment TypeTool to create a new appointment type in Follow Up Boss.
Create CallTool to add a call record to Follow Up Boss.
Create Custom FieldTool to create a custom field in Follow Up Boss.
Create Deal Custom FieldTool to create a custom field for deals in Follow Up Boss.
Create DealTool to create a new deal in Follow Up Boss.
Create Email Marketing CampaignTool to create an email marketing campaign in Follow Up Boss.
Create Email Marketing EventsTool to notify Follow Up Boss about marketing emails sent, opens, clicks, bounces, unsubscribes and spam reports.
Create EventsTool to send in a lead or an event related to a lead in Follow Up Boss.
Create GroupTool to create a new Follow Up Boss group with specified members and distribution settings.
Create PipelineTool to create a new pipeline in Follow Up Boss.
Create PondsTool to create a new pond in Follow Up Boss.
Create ReactionsTool to add a reaction (emoji) to a Note, Call, or ThreadedReply.
Create StageTool to create a new stage in Follow Up Boss.
Create TeamTool to create a new team in Follow Up Boss.
Create email templateTool to create a new email template in Follow Up Boss.
Create Text Message TemplateTool to create a text message template in Follow Up Boss.
Delete AppointmentTool to delete an appointment by ID.
Delete Appointment OutcomeTool to delete an appointment outcome by ID.
Delete Appointment TypeTool to delete an appointment type by its ID.
Delete Custom FieldTool to delete a custom field by its ID.
Delete DealTool to delete a deal by its ID.
Delete Deal Custom FieldTool to delete a deal custom field by ID.
Delete GroupTool to delete a group by its ID.
Delete People RelationshipTool to delete a people relationship by ID in Follow Up Boss.
Delete PipelineTool to delete a pipeline by its ID from Follow Up Boss.
Delete PondTool to delete a pond by its ID.
Delete StageTool to delete a Follow Up Boss stage by ID.
Delete TeamTool to delete a team by its ID.
Delete text message templateTool to delete a text message template by ID.
Get AppointmentTool to retrieve an appointment by its ID.
Get Appointment OutcomeTool to retrieve an appointment outcome by ID.
Get Appointment TypeTool to retrieve an appointment type by ID.
Get CallTool to retrieve a call by its ID from Follow Up Boss.
Get DealTool to retrieve a deal by its ID from Follow Up Boss.
Get Deal Custom FieldTool to retrieve a deal custom field by its ID from Follow Up Boss.
Get EventTool to retrieve a single event by its ID from Follow Up Boss.
Get GroupTool to retrieve a group by its ID from Follow Up Boss.
Get IdentityTool to retrieve identity and authentication information from Follow Up Boss.
Get MeTool to retrieve information about the currently authenticated user.
Get People RelationshipTool to retrieve a people relationship by its ID from Follow Up Boss.
Get PipelineTool to retrieve a pipeline by its ID from Follow Up Boss.
Get PondsTool to retrieve a pond by its ID from Follow Up Boss.
Get Smart ListTool to retrieve a Smart List by its ID from Follow Up Boss.
Get StageTool to retrieve a stage by its ID from Follow Up Boss.
Get TeamTool to retrieve a team by its ID from Follow Up Boss.
Get TemplateTool to retrieve an email template by its ID from Follow Up Boss.
Get Text MessageTool to retrieve a text message by its ID from Follow Up Boss.
Get Text Message TemplateTool to retrieve a text message template by its ID from Follow Up Boss.
Get UserTool to retrieve a user by its ID from Follow Up Boss.
List Action PlansTool to get a list of Action Plans from Follow Up Boss.
List Action Plans PeopleTool to list Action Plans applied to a particular person or list people on a particular Action Plan.
List Appointment OutcomesTool to list all appointment outcomes from Follow Up Boss.
List AppointmentsTool to search for appointments in Follow Up Boss.
List Appointment TypesTool to list all appointment types from Follow Up Boss.
List CallsTool to search for calls in Follow Up Boss.
List Custom FieldsTool to list all custom fields in Follow Up Boss.
List Deal Custom FieldsTool to list all deal custom fields in Follow Up Boss.
List DealsTool to search for and list deals from Follow Up Boss.
List Email Marketing CampaignsTool to list email marketing campaigns from Follow Up Boss.
List Email Marketing EventsTool to retrieve email marketing events from Follow Up Boss.
List EventsTool to search for and list events from Follow Up Boss.
List GroupsTool to list all groups from Follow Up Boss.
List Groups Round RobinTool to list groups with round-robin data from Follow Up Boss.
List Inbox AppsTool to list all inbox app installations from Follow Up Boss.
List People RelationshipsTool to list all people relationships from Follow Up Boss.
List PipelinesTool to search for pipelines in Follow Up Boss.
List PondsTool to list all ponds from Follow Up Boss.
List Smart ListsTool to list Smart Lists from Follow Up Boss.
List StagesTool to retrieve a list of stages from Follow Up Boss.
List Team InboxesTool to list all shared team inboxes from Follow Up Boss.
List TeamsTool to get a list of teams from Follow Up Boss.
List TemplatesTool to list all email templates from Follow Up Boss.
List Text MessagesTool to list text messages for a person or phone number from Follow Up Boss.
List Text Message TemplatesTool to list all text message templates from Follow Up Boss.
List TimeframesTool to get a list of timeframes from Follow Up Boss.
List UsersTool to search for and list users from Follow Up Boss.
List WebhooksTool to retrieve a list of webhooks from Follow Up Boss.
Merge TemplateTool to merge an email template with person data using Follow Up Boss API.
Merge Text Message TemplateTool to merge a text message template with person data.
Update Action Plan People StatusTool to update the status of an Action Plan to Person relationship in Follow Up Boss.
Update AppointmentTool to update an existing appointment in Follow Up Boss.
Update appointment outcomeTool to update an existing appointment outcome in Follow Up Boss.
Update Appointment TypeTool to update an existing appointment type in Follow Up Boss.
Update CallTool to update an existing call record in Follow Up Boss.
Update Custom FieldsTool to update an existing custom field in Follow Up Boss by its ID.
Update Deal Custom FieldsTool to update an existing deal custom field in Follow Up Boss.
Update DealTool to update an existing deal in Follow Up Boss.
Update Email Marketing CampaignTool to update an existing email marketing campaign in Follow Up Boss.
Update GroupTool to update an existing Follow Up Boss group with modified members and distribution settings.
Update People RelationshipsTool to update details of a specific people relationship in Follow Up Boss.
Update PipelineTool to update an existing pipeline in Follow Up Boss.
Update PondsTool to update an existing pond in Follow Up Boss.
Update StageTool to update an existing stage in Follow Up Boss.
Update TeamTool to update an existing team in Follow Up Boss.
Update email templateTool to update an existing email template in Follow Up Boss.
Update Text Message TemplateTool to update an existing text message template in Follow Up Boss.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Follow Up Boss account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Follow Up Boss

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Follow Up Boss access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called follow up boss_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["follow_up_boss"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Follow Up Boss actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Follow Up Boss actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, follow up boss)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Follow Up Boss tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Follow Up Boss database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Follow Up Boss

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Follow Up Boss, then start asking questions.

Complete Code

Here's the complete code to get you started with Follow Up Boss and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["follow_up_boss"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Follow Up Boss actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Follow Up Boss actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Follow Up Boss to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Follow Up Boss tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Follow Up Boss MCP Agent with another framework

FAQ

What are the differences in Tool Router MCP and Follow Up Boss MCP?

With a standalone Follow Up Boss MCP server, the agents and LLMs can only access a fixed set of Follow Up Boss tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Follow Up Boss and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Follow Up Boss tools.

Can I manage the permissions and scopes for Follow Up Boss while using Tool Router?

Yes, absolutely. You can configure which Follow Up Boss scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Follow Up Boss data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.