Skip to main content
Glama

HubSpot MCP Server

A Model Context Protocol (MCP) server that provides tools for interacting with HubSpot CRM. This server allows you to create, update, delete, and fetch summary records (stored as Note engagements) in HubSpot.

DockerFile

  • docker build -t mcp-hubspot-ts .

  • docker run --env-file .env -it mcp-hubspot-ts

Related MCP server: BackCrew HubSpot MCP Server

Features

  • Create a summary as a Note engagement in HubSpot

  • Fetch all summary records (Notes) from HubSpot

  • Filter summary records by date

  • Update existing summary records

  • Delete summary records

  • Send summary records via chat or email

Testing with MCP Inspector

To inspect and test your MCP server implementation, you can use the MCP Inspector. For example:

npx @modelcontextprotocol/inspector -e HUBSPOT_ACCESS_TOKEN=your_access_token_here node build/index.js

This will start the MCP Inspector UI on http://localhost:5173. Use the UI to send JSON-RPC requests to your server.

Env

Create a .env file in the project root with your HubSpot credentials:

HUBSPOT_ACCESS_TOKEN=your_access_token_here
SHARED_CONTACT_ID=your_contact_id_here

License

This project is licensed under the MIT License - see the LICENSE file for details.

Related MCP Connectors

Related MCP Servers

  • A
    license
    B
    quality
    D
    maintenance
    Enables AI assistants to interact with a HubSpot CRM account via natural language, starting with read-only lookups and optionally enabling write operations like creating contacts, deals, and notes.
    11
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables Claude to search, create, and update contacts, deals, and support tickets in HubSpot, and to generate cross-object account summaries.
    10
    MIT
  • F
    license
    Not graded
    quality
    A
    maintenance
    Enables AI assistants to interact with HubSpot CRM data, including creating contacts and companies, retrieving activity and conversations, and performing semantic search over stored interactions while using vector storage and caching for faster responses.
    -