How to Use the Follow Up Boss MCP in LlamaIndex

Q: How do the Follow Up Boss MCP tools work with a LlamaIndex agent?

You wrap the MCP client in the McpToolSpec provided by LlamaIndex. This converts all the available Follow Up Boss tools into a format the agent can use for both direct execution and data indexing. It's a straightforward way to make your CRM data available for RAG.

Turn your Follow Up Boss data into a queryable knowledge base using LlamaIndex. Ask questions, get answers from your live CRM.

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 LlamaIndex

Create your Vinkius account to connect Follow Up Boss to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Live CRM Data

LlamaIndex doesn't just call an API; it ingests and remembers the results. You can set up a process to periodically run tools like `list_people`, `list_deals`, and `list_tasks`, feeding the output directly into a vector index. It's like giving your AI a perfect memory of your CRM. Once indexed, this data becomes a searchable knowledge base. Your agent no longer needs to make dozens of API calls to find something. It can perform a single semantic search across the indexed data to get the answer instantly.

Answer Questions with Real Data

Stop dealing with agents that hallucinate about your pipeline. When you ask, "What's the status of the Miller deal and who was the last person to contact them?", a LlamaIndex agent queries its knowledge base first. It pulls context from previous runs of `get_deal` and `list_person_notes` to give you a summary grounded in facts. This is Retrieval-Augmented Generation (RAG) for your real estate business. The agent's response is built directly from the data it retrieved from Follow Up Boss, so you can trust the answers you get about your own customers and deals.

Build RAG Agents with a LlamaIndex MCP Server

Combine your indexed Follow Up Boss data with other knowledge sources. You can add property listing PDFs, local market analysis documents, and your team's training manuals into the same index. Your agent gets a complete operational picture. Now, your agent can answer complex questions by pulling information from both your live CRM data via this MCP server and your static documents. Ask it to "find all deals over $500k in the Northwood district and summarize the market trends there," and it will use all available data to construct the answer.

Setup guide

Set up Follow Up Boss MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Follow Up Boss MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Follow Up Boss tools.",
)
response = await agent.run("List recent Follow Up Boss data")

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 LlamaIndex

You wrap the MCP client in the `McpToolSpec` provided by LlamaIndex. This converts all the available Follow Up Boss tools into a format the agent can use for both direct execution and data indexing. It's a straightforward way to make your CRM data available for RAG.

Yes, you have full control. When creating the tool specification, you can provide an `allowed_tools` filter to expose only certain functions, like `list_deals` and `list_people`. This ensures your agent only indexes and interacts with the specific Follow Up Boss data you've approved.

After you've indexed the data from the MCP server, you build a query engine in LlamaIndex. Then you can ask it natural language questions. The engine translates your question into a vector search against the indexed data to find the most relevant information and generate a response.

It augments it. You'll still use the MCP server for real-time actions like `create_person` or `add_note`. The indexed data is for fast, context-rich querying, while direct tool calls are for when you need the absolute latest data or need to change something in the CRM.

It is. LlamaIndex indexes the Follow Up Boss data you retrieve—like contact details and deal histories—into a vector store that you control. This MCP server encrypts data in transit, and you decide where that index is stored, whether it's on your local machine or in your private cloud account.

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