How to Use the Follow Up Boss MCP in LlamaIndex

Q: How do I limit which Follow Up Boss tools the LlamaIndex agent can access?

Use the allowedtools filter when setting up your tool spec. You can restrict the agent to only use listcalendarappointments if you want to prevent it from modifying records.

Q: Does the LlamaIndex agent know when new events happen in the CRM?

Not automatically. You need to periodically run listrecentevents and re-index the outputs to keep your vector store current with the live database.

Index your real estate pipeline with LlamaIndex and query your Follow Up Boss CRM using natural language.

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 Follow Up Boss MCP Server data

LlamaIndex does not just execute API calls. It takes the output from `list_leads` and `get_lead_details` and embeds that data into a vector store. You can now run semantic queries across your entire database of buyers and sellers without writing SQL. When an agent asks about recent high-budget buyers, the system searches the indexed profiles instead of hallucinating. It grounds every answer in the actual contact records pulled from your CRM endpoints.

Build RAG applications over agent notes

Brokers leave thousands of touchpoints buried in the CRM. By connecting this tool, LlamaIndex pulls records using `list_person_notes` and `list_recent_events`. It builds a searchable knowledge base of every text, call, and website visit your team logged. A broker can ask for a summary of a specific client's hesitations over the last six months. The LlamaIndex query engine retrieves the exact notes, synthesizes the context, and gives you a factual breakdown of the relationship history.

Correlate tasks with closed transactions

The MCP protocol lets your application pull active transactions via `list_real_estate_deals` and cross-reference them with pending actions from `list_followup_tasks`. Your pipeline data is useless if you cannot query it easily. You feed these lists into your unified index. Now your internal RAG tool can answer complex questions about which pending tasks are blocking your highest-value deals from closing this month.

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

Install the llama-index-tools-mcp package. Set up a BasicMCPClient, wrap it in an McpToolSpec, and call to_tool_list_async() to feed the endpoints to your FunctionAgent.

Yes. While it excels at reading data, your agent can still execute the `create_new_lead` tool. It just needs essential details like a name or email address.

Use the allowed_tools filter when setting up your tool spec. You can restrict the agent to only use `list_calendar_appointments` if you want to prevent it from modifying records.

Not automatically. You need to periodically run `list_recent_events` and re-index the outputs to keep your vector store current with the live database.

The MCP server operates inside a strict V8 Isolate Sandbox. When LlamaIndex retrieves buyer emails and phone numbers via `get_lead_details`, the transport layer is fully encrypted. Vinkius drops the instance the moment your query finishes.

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