HubSpot Integration MCP Server

Customer Data PlatformsPython

Connect AI assistants to HubSpot CRM data with semantic search capabilities

Available Tools

hubspot_create_contact

Create contacts in HubSpot with duplicate prevention

hubspot_create_company

Create companies in HubSpot with duplicate prevention

hubspot_get_company_activity

Retrieve activity for specific companies

hubspot_get_active_companies

Retrieve most recently active companies

hubspot_get_active_contacts

Retrieve most recently active contacts

hubspot_get_recent_conversations

Retrieve recent conversation threads with messages

hubspot_search_data

Semantic search across previously retrieved HubSpot data

A powerful integration that enables AI assistants to interact directly with HubSpot CRM data. This server bridges AI models with your HubSpot account, providing seamless access to contacts, companies, and engagement data. Built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times. The implementation prioritizes the most frequently used, high-value HubSpot operations with robust error handling and API stability. Each component is optimized for AI-friendly interactions, ensuring reliable performance even during complex, multi-step CRM workflows.

Overview

The HubSpot Integration MCP server enables AI assistants to interact directly with your HubSpot CRM data. This integration provides significant benefits including direct CRM access without intermediary steps, context retention through vector storage with FAISS for semantic search across previous interactions, and simple deployment with minimal configuration.

Setup Instructions

Prerequisites

Before using this MCP, you'll need a HubSpot access token with the following scopes:

crm.objects.contacts (read/write)
crm.objects.companies (read/write)
sales-email-read

Installation Options

Option 1: Using Smithery (Recommended)

The simplest way to install is using Smithery:

npx -y @smithery/cli@latest install mcp-hubspot --client claude

Option 2: Using Docker Directly

You can run the Docker image directly with your HubSpot access token:

docker run -e HUBSPOT_ACCESS_TOKEN=your_token buryhuang/mcp-hubspot:latest

Option 3: Manual Configuration in Claude Desktop

Add the following configuration to your Claude desktop settings:

{
  "mcpServers": {
    "hubspot": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "HUBSPOT_ACCESS_TOKEN=your_token",
        "-v", "/path/to/storage:/storage",
        "buryhuang/mcp-hubspot:latest"
      ]
    }
  }
}

Replace your_token with your actual HubSpot access token. The volume mount for storage is optional but recommended for data persistence.

Building the Docker Image Locally

If you prefer to build the Docker image yourself:

Clone the repository:

git clone https://github.com/peakmojo/mcp-hubspot.git
cd mcp-hubspot

Build the Docker image:

docker build -t mcp-hubspot .

For multi-platform builds:

docker buildx create --use
docker buildx build --platform linux/amd64,linux/arm64 -t your-username/mcp-hubspot:latest --push .

Usage Examples

Once configured, you can use the HubSpot integration with prompts like:

Create HubSpot contacts and companies from this LinkedIn profile:
[Paste LinkedIn profile text]

What's happening lately with my pipeline?

Find all recent conversations with customer XYZ

The MCP will handle the interaction with HubSpot's API, retrieve the relevant data, and provide it to the AI assistant for processing and response.

Performance Features

This integration includes several performance-enhancing features:

Vector Storage: Utilizes FAISS for efficient semantic search and retrieval
Thread-Level Indexing: Stores each conversation thread individually for precise retrieval
Embedding Caching: Uses SentenceTransformer with automatic caching
Persistent Storage: Data persists between sessions in configurable storage directory
Multi-platform Support: Optimized Docker images for various architectures