How to Use the HubSpot Analytics MCP in LlamaIndex

Q: How does LlamaIndex use HubSpot Analytics to improve query accuracy?

LlamaIndex indexes the output of tools like hswebanalytics into a vector store. When you ask a question, it retrieves the relevant, factual data from that index first, then uses the LLM to formulate an answer based on real numbers.

Q: Can I build a LlamaIndex agent to monitor specific HubSpot Analytics reports?

Yes. You can create an agent that periodically calls hslistreports to check for new reports. It can then use other tools like hsemailanalytics to pull data from any reports that match certain criteria you define.

Q: Is it possible for a LlamaIndex agent to track a user journey with HubSpot Analytics?

Absolutely. You can configure an agent to use hslistevents for a specific contact ID. By indexing these events over time, your agent can answer questions about that contact's entire journey, from first page view to recent email opens.

Index your HubSpot Analytics data into a knowledge base. Build LlamaIndex RAG apps that answer questions with facts, not guesses.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot Analytics MCP to LlamaIndex

Create your Vinkius account to connect HubSpot Analytics 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 HubSpot Analytics with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn API Calls into a Searchable Memory

Don't let good data go to waste. LlamaIndex can automatically index the output from every tool call. When your agent runs `hs_email_analytics`, the results are added to a vector store. Later, you can ask questions about past performance without making another API call. This creates a private, searchable history of your marketing metrics. You can ask, 'Which campaign had the highest open rate in Q2?' and LlamaIndex will retrieve the answer from your indexed data, giving you a response grounded in actual numbers you've already pulled.

Build a RAG Pipeline on Your HubSpot Data

Combine live API data with your own documents. First, use `hs_list_reports` and `hs_web_analytics` to pull down your core metrics and available reports. LlamaIndex ingests this structured data into a queryable index. Now, your agent can answer complex questions by retrieving context from that index. Ask it 'Summarize our website's lead generation trends from our main traffic sources,' and it will use the indexed `hs_web_analytics` data to give you a factual, synthesized answer.

Query a Customer's Entire History

Create a complete picture of any contact or deal. Use the `hs_list_events` tool to pull the activity timelines for your most important customers and index them. This gives your agent a powerful knowledge base for understanding customer behavior. Instead of just seeing a list of events, you can ask semantic questions. For instance, 'Show me deals that had a meeting scheduled after viewing the pricing page.' LlamaIndex can find these patterns by querying the indexed event data from HubSpot.

Setup guide

Set up HubSpot Analytics 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 HubSpot Analytics 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 HubSpot Analytics tools.",
)
response = await agent.run("List recent HubSpot Analytics 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 HubSpot. 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 HubSpot Analytics 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 HubSpot Analytics MCP in LlamaIndex

LlamaIndex indexes the output of tools like `hs_web_analytics` into a vector store. When you ask a question, it retrieves the relevant, factual data from that index first, then uses the LLM to formulate an answer based on real numbers.

Yes. You can create an agent that periodically calls `hs_list_reports` to check for new reports. It can then use other tools like `hs_email_analytics` to pull data from any reports that match certain criteria you define.

Absolutely. You can configure an agent to use `hs_list_events` for a specific contact ID. By indexing these events over time, your agent can answer questions about that contact's entire journey, from first page view to recent email opens.

It's straightforward. After installing the MCP extension, you use the `McpToolSpec` and point it to your Vinkius server URL. LlamaIndex handles converting the tools for your agent automatically.

The MCP server itself doesn't store anything. Your LlamaIndex application, running on your own infrastructure, receives the data (like web traffic stats or email campaign metrics) and indexes it into the vector store you control.

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