hubspot_create_contactLABSCO SUMMARY
The CRM remembers what you already pulled out of it.
Two things are slow with HubSpot: getting records in from unstructured text, and finding a conversation you half remember. Creation handles duplicates itself, and everything retrieved is indexed for semantic search — so the second time you ask, the answer is already local.
What it is
A HubSpot CRM client focused on the operations that come up daily: creating contacts and companies with duplicate prevention, reading recent activity, and searching what has been retrieved. Retrieved data is indexed with FAISS, so the search is semantic and survives between sessions.
What you get
- Contacts and companies created, with duplicate prevention on both
- The most recently active companies and the most recently active contacts
- Activity for a specific company
- Recent conversation threads with their messages, indexed thread by thread
- Semantic search across everything previously retrieved, backed by a FAISS vector store
- Storage that persists between sessions, in a directory you configure
Requirements
A HubSpot access token with the CRM scopes the tools use. It deploys as a Docker image, with images built for several architectures; SentenceTransformer produces the embeddings, and caches them automatically.
Setup effort
Run a container — pull the image and point your client at it
USE CASES
01
Turning a profile or a note into CRM records
Paste what you have and get the contact and the company created, with duplicates caught rather than created.
02
Catching up on the pipeline
Read the most recently active companies and contacts to see what has moved since you last looked.
03
Preparing for a call
Pull the account's recent activity and the conversation threads behind it before you dial.
04
Finding the conversation you half remember
Search semantically across what has already been retrieved, on what was said rather than on an exact field match.
7 tools
Listed in project docs. Your client may show a different list.
hubspot_create_companyhubspot_get_company_activityhubspot_get_active_companieshubspot_get_active_contactshubspot_get_recent_conversationshubspot_search_dataBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation. There is no update, delete, deal or ticket tool; it creates and reads contacts, companies and conversations only.
Requires
HUBSPOT_ACCESS_TOKEN in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"hubspot": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"HUBSPOT_ACCESS_TOKEN=<YOUR_HUBSPOT_ACCESS_TOKEN>",
"-v",
"<YOUR_PATH_TO_STORAGE>:/storage",
"buryhuang/mcp-hubspot:latest"
]
}
}
}
