mcpField
H
Hubspot

Hubspot

Remote
pipeworx.ioBusiness & Marketing0Updated 2d ago

About Hubspot

Hubspot is an MCP server for reading contacts, companies, and deals from a connected HubSpot workspace. It supports browsing, searching contacts, and retrieving individual records with their associated properties and links.

Key features

  1. 01List and search contacts
  2. 02Retrieve full contact profiles
  3. 03List companies and retrieve company profiles
  4. 04List deals and retrieve deal details
  5. 05View deal links to contacts and companies

Use cases

  1. 01Find a contact by name or email
  2. 02Review a contact’s custom properties
  3. 03Check company or deal records
  4. 04Inspect a deal’s stage and linked records

MCP support

Exposes HubSpot contact, company, and deal operations to MCP clients through Pipeworx or as a local stdio MCP server. Gateway access requires a connected HubSpot account.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/hubspot/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-hubspot

HubSpot MCP Pack

Part of Pipeworx — an MCP gateway connecting AI agents to 1881+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
hs_list_contactsBrowse all contacts in your HubSpot workspace. Returns contact IDs, names, emails, and properties. Paginate with limit and after parameters.
hs_get_contactFetch a contact's full profile by ID. Returns name, email, phone, company, and all custom properties.
hs_search_contactsSearch contacts by name, email, or custom properties. Use when you need to find specific people in your database.
hs_list_companiesBrowse all companies in your HubSpot workspace. Returns company IDs, names, domains, and properties. Paginate with limit and after parameters.
hs_get_companyFetch a company's full profile by ID. Returns name, domain, industry, revenue, and all custom properties.
hs_list_dealsBrowse all deals in your HubSpot workspace. Returns deal IDs, names, amounts, pipeline stages, and close dates. Paginate with limit and after parameters.
hs_get_dealFetch a deal's full details by ID. Returns deal name, amount, stage, owner, and linked contacts and companies.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "hubspot": {
      "url": "https://gateway.pipeworx.io/hubspot/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/hubspot/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1881+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack runs against a connected hubspot account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect hubspot, then call POST https://gateway.pipeworx.io/v1/tools/hs_list_contacts with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/hs_list_contacts. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "hubspot": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-hubspot"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-hubspot

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Hubspot data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.