Integration
Use HubSpot with Claude, GPT, Gemini and more
Connect HubSpot once, then ask any model in llmwise to read from it and act in it: 262 actions, with every write shown to you before it runs.
Actions (toolkit version 20260915_00) checked against Composio's HubSpot toolkit page. Updated .
Short answer
HubSpot connects to llmwise in one click, and every model can then use its 262 actions: 112 that read and run on their own, and 150 that write and ask you first (65 of them every time). On paid plans, included in the message price.
Try it: HubSpot in one message
Send this with any model. The model finds HubSpot's actions for the job and runs them, and the reply shows each one.
Which HubSpot deals closing this month haven't moved in two weeks? Add a note on each with the next step.
| Action | In llmwise |
|---|---|
| Search deals | Reads: runs without asking |
| Create note | Writes: asks first |
The reads run straight away; the write waits on an approval card with Allow and Deny, and shows what it will do first.
What the model can do in HubSpot
262 actions in all. Below: the 13 Composio marks as HubSpot's main ones, and 17 more. The other 232 are there too, and the model finds them when a job needs one.
Reads: runs without asking
- Get pipeline stage audit
- List company activities
- List company meetings
- List deal activities
- Batch read associations
- Who Am I
Writes: asks first
- Create Contact From Natural Language
- Create CRM Object From Natural Language
- Create Deal From Natural Language
- Create meeting
- Create object association
- Create product
- Create tickets
- Add asset association
- Archive batch of feedback submissions by id
Always asks first
- Add token to event template
- Archive batch of line items by id
- Archive batch of objects by id
- Archive batch of properties
- Archive a batch of quotes by id
- Archive companies
- Archive company
- Archive contact
- Archive contacts
- Archive a CRM object by ID
- Archive deals
- ArchiveEmail email
- Archive emails
- Archive feedback submission
- Archive line item by id
What asks first, and why
Reading needs no approval. Anything that writes asks first, and sending, deleting, payments and sharing always ask.
In HubSpot, that means add token to event template, archive batch of line items by id, archive batch of objects by id, and archive batch of properties always wait for your yes.
Always allow can switch off the question for one of HubSpot's 85 other writes, and a reply that has read outside content asks again anyway. One reply runs up to 10 actions, each result read up to 50,000 characters.
Where your HubSpot data goes
Each action runs through Composio and HubSpot's own service, which receive its inputs; the result is shown in your chat and saved with it. Composio holds the sign-in, encrypted. More in the Privacy Policy.
More apps
100+ apps connect in one click · 1,500+ in Composio's catalog. Every app with its own page, or add a remote server of your own with the MCP client.
Questions
How do I connect HubSpot to llmwise?
In Settings → Connectors, press Connect next to HubSpot and sign in on HubSpot's own page: one click, no setup. Composio holds the connection, and llmwise never sees your password. On a paid plan.
Which AI models work with HubSpot, and what does it cost?
Any of the 15 models in llmwise, from GLM 5.3 Flash to Claude Fable 5.1: HubSpot's actions are the same whichever you pick. Connectors are on the paid plans (Pro ($20 a month), Max ($50 a month), Ultra ($100 a month), and Studio ($200 a month)), included in the message price.
Claude, GPT, Gemini, DeepSeek, Grok, Kimi, and GLM, in one chat.
See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.