How to Use the HubSpot CRM (Full) MCP in LlamaIndex

Q: How do I configure HubSpot CRM (Full) with LlamaIndex?

Install llama-index-tools-mcp via pip. Initialize a BasicMCPClient with your endpoint URL, wrap it in McpToolSpec, and pass the async tool list to your FunctionAgent.

Q: Does the system know our custom sales stages?

It reads them directly. The hslistpipelines tool returns your specific stage labels, IDs, and display order. LlamaIndex incorporates this exact structure into the context window.

Q: Can I restrict which tools my LlamaIndex agent uses?

You can. The framework supports an allowedtools filter. You might expose hssearchcontacts for RAG lookups while blocking hscreatedeal to prevent accidental pipeline changes.

Index live HubSpot CRM data into your LlamaIndex vector stores and build RAG applications grounded in actual sales records.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HubSpot CRM (Full) MCP to LlamaIndex

Create your Vinkius account to connect HubSpot CRM (Full) 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 CRM (Full) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vectorizing deal histories

The `hs_search_deals` tool pulls live pipeline stages, monetary amounts, and expected close dates directly into your LlamaIndex knowledge base. Your RAG application queries the actual CRM state instead of relying on stale exports. It indexes the exact deal names and owner assignments. Look, users need answers backed by hard data. When someone asks about Q3 revenue, the query engine searches the vector store containing the latest opportunity records. The system grounds its response in the specific numbers returned by the API.

RAG over LlamaIndex MCP Server tickets

Passing `hs_search_tickets` to your FunctionAgent allows it to index customer support requests by subject and priority. The framework ingests the HIGH, MEDIUM, and LOW status labels alongside the pipeline category. This creates a searchable semantic index of every open customer issue. Support managers can ask natural language questions about recurring bugs. The engine retrieves the relevant ticket IDs and creation dates from the index. If action is required, the agent can immediately trigger `hs_create_note` to log an update on the affected records.

Grounded company insights

Running `hs_search_companies` fetches annual revenue, employee counts, and website domains for semantic indexing. Your application builds a unified context window combining these hard CRM metrics with your internal documentation. The agent knows exactly which industry a target account belongs to. This kills hallucination during account research. The framework pulls the assigned owner from the tool output and adds it to the RAG context. Sales reps querying the system get accurate organizational details straight from the source.

Setup guide

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

Install `llama-index-tools-mcp` via pip. Initialize a `BasicMCPClient` with your endpoint URL, wrap it in `McpToolSpec`, and pass the async tool list to your FunctionAgent.

The current tools focus on core records. You index company details with `hs_search_companies` and deal amounts with `hs_search_deals`, then build a vector store from those results.

It reads them directly. The `hs_list_pipelines` tool returns your specific stage labels, IDs, and display order. LlamaIndex incorporates this exact structure into the context window.

You can. The framework supports an allowed_tools filter. You might expose `hs_search_contacts` for RAG lookups while blocking `hs_create_deal` to prevent accidental pipeline changes.

Authentication requires a single endpoint token, and the execution environment is completely isolated. When your indexer pulls monetary amounts via `hs_search_deals`, the Vinkius infrastructure processes the request in a temporary sandbox that vanishes after the call.

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