MCP Catalogs
← Home

mcp-hubspot

by baryhuang·★ 122·Score 44

MCP server for HubSpot CRM integration with vector storage and caching to overcome API limitations.

ecommerceai-llmproductivity
61
Forks
2
Open issues
6 mo ago
Last commit
2d ago
Indexed

Overview

The mcp-hubspot server enables AI assistants to interact directly with HubSpot CRM data through a Model Context Protocol implementation. It provides tools for managing contacts and companies, retrieving activity data, and performing semantic searches across previously retrieved data. The implementation includes built-in vector storage using FAISS and embedding caching to improve performance and overcome HubSpot API limitations.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI-powered CRM data analysis and reporting
you:Creating contacts and companies from external sources like LinkedIn
you:Semantic search across CRM data for better customer insights
you:What is the purpose of vector storage in this MCP server?
you:How does this server handle HubSpot API limitations?

When to choose this

Choose this if you need AI assistants to interact with your HubSpot CRM data, especially if you require semantic search capabilities and want to overcome API limitations through caching.

When NOT to choose this

Don't choose this if you need access to HubSpot features not covered by the available tools or if you require a different CRM platform integration.

Tools this server exposes

7 tools extracted from the README
  • hubspot_create_contact

    Create contacts with duplicate prevention

  • hubspot_create_company

    Create companies 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

Comparable tools

mcp-salesforcemcp-zoho-crmhubspot-api-python

Installation

Installation

**Via Smithery (recommended)**

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

**Using Docker**

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

**Claude Desktop Configuration**

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

**Prerequisites**

  • HubSpot access token with these scopes:

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

FAQ

What is the purpose of vector storage in this MCP server?
The vector storage using FAISS enables semantic search across previously retrieved HubSpot data, allowing AI assistants to find relevant information based on meaning rather than just keywords.
How does this server handle HubSpot API limitations?
The implementation includes embedding caching and thread-level indexing to overcome API rate limits and improve response times while maintaining data persistence between sessions.

Compare mcp-hubspot with

mcp-hubspot vs ultimate_mcp_servermcp-hubspot vs mcp-server-chartmcp-hubspot vs everythingmcp-hubspot vs filesystemmcp-hubspot vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.