How to Use the HubSpot Sales Hub MCP in LlamaIndex

Q: How do I load HubSpot Sales Hub tools into LlamaIndex?

Install llama-index-tools-mcp. Create a BasicMCPClient with your Vinkius URL, wrap it in an McpToolSpec, and call await mcptoolspec.totoollistasync(). Pass the resulting list to your FunctionAgent.

Q: Can LlamaIndex search through HubSpot Sales Hub deals?

Yes. The agent uses hssearchdeals to pull specific opportunities based on name or owner. It then indexes those results so you can run semantic queries against your active pipeline.

Q: Does the LlamaIndex agent need to know internal HubSpot Sales Hub pipeline IDs?

The agent uses hslistpipelines to map human-readable stage names to internal HubSpot IDs. It caches these references in its index to ensure future deal creations land in the correct stage.

Q: Can I filter which MCP tools the agent accesses?

You pass an allowedtools list when configuring the tool spec. This restricts the agent to read-only operations like checking meetings if you want to prevent it from modifying deals.

Index your HubSpot pipeline directly into LlamaIndex. Turn deals, products, and quotes into a queryable knowledge base for your RAG applications.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot Sales Hub MCP to LlamaIndex

Create your Vinkius account to connect HubSpot Sales Hub 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 Sales Hub with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index deals and pipelines for RAG

`hs_search_deals` and `hs_deals_by_stage` return raw pipeline data that LlamaIndex instantly vectorizes. Your RAG application ingests current deal amounts, close dates, and owner assignments directly from the CRM. When a user asks about pipeline health, the agent queries the vector store instead of guessing. This grounds your AI client in actual sales reality. The framework automatically converts the returned JSON into searchable nodes. You get answers based on live pipeline stages, completely eliminating hallucinations about revenue projections.

Query the HubSpot Sales Hub MCP Server

`hs_list_quotes` and `hs_list_meetings` pull historical sales interactions into your semantic search index. Your agent retrieves pending quote statuses and meeting outcomes to build context around specific accounts. It cross-references a rejected proposal with the notes from the last logged call. You combine this structured CRM data with unstructured documents. The agent pulls a specific quote ID and matches it against your internal pricing PDFs. The user gets a synthesized answer that respects both internal policy and actual prospect history.

Manage products and catalog pricing

`hs_search_products` and `hs_create_product` allow your LlamaIndex agent to read and write catalog items based on user queries. The agent checks current SKUs and default unit prices before generating a proposal draft. If a new service tier is needed, it creates the product directly in the CRM. The framework maps the product library into your knowledge graph. Sales reps ask the agent for pricing on specific configurations, and it retrieves the exact HubSpot ID required for line-item attachment. No one has to switch tabs to find a SKU again.

Setup guide

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

Install `llama-index-tools-mcp`. Create a `BasicMCPClient` with your Vinkius URL, wrap it in an `McpToolSpec`, and call `await mcp_tool_spec.to_tool_list_async()`. Pass the resulting list to your `FunctionAgent`.

Yes. The agent uses `hs_search_deals` to pull specific opportunities based on name or owner. It then indexes those results so you can run semantic queries against your active pipeline.

The agent uses `hs_list_pipelines` to map human-readable stage names to internal HubSpot IDs. It caches these references in its index to ensure future deal creations land in the correct stage.

You pass an `allowed_tools` list when configuring the tool spec. This restricts the agent to read-only operations like checking meetings if you want to prevent it from modifying deals.

Vinkius isolates your connection using a zero-trust architecture. Your SKUs, unit prices, and product descriptions pass through a dedicated endpoint token without touching persistent storage. The server handles the authentication securely and drops the connection state the second the RAG ingestion completes.

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