You want to point Claude at your HubSpot CRM and say standardize every company description, tighten the deal notes from last quarter, and fix the custom-object copy that drifted across teams. What stops you is the CRM itself. The whole team works in it, reporting and workflows run on it, and most ways of wiring AI to a CRM write straight to it, so one bad pass corrupts records and trips automations before you can check it.
Scratch changes where the edit happens. Claude does 99% of the work, reading and rewriting every record as files on your laptop. The last 1%, deciding what actually writes back, stays with you. Nothing reaches the live CRM until you have seen the change as a diff and approved it.
How it works
- Scratch pulls your CRM into files. Contacts, companies, deals, tickets, and the rest come down to a folder on your laptop, one file per record.
- Claude edits the records. Open the folder in the Claude desktop app. Try a prompt on a few records in Chat, then let Cowork or Code run it across a whole object. Standardize every company description and tighten the deal notes from last quarter. Claude edits the files, never the live CRM.
- You review every diff and publish. Scratch shows each changed field next to the original, word by word. Approve what ships, and Scratch writes only those records back through the HubSpot CRM API.
What people use it for
Most people arrive with a CRM that has drifted, because cleaning it by hand means opening every record one at a time.
- Standardize company descriptions across every account.
- Tighten deal notes and next steps after a quarter of drift.
- Clean up custom-object copy that diverged across teams.
- Normalize the formatting on a property so reports and filters behave.
- Fill missing fields by reading what is already on the record.
Pull a few hundred records to feel the loop, then point Claude at the whole object.
Why not an MCP server?
A HubSpot MCP server or app hands Claude a direct line to your live CRM. The write button is wired straight in, so one bad pass rewrites every record at once, fires the workflows watching those fields, and your reps clean it up by hand.
Scratch gives Claude the same full read and write access, but against a local copy. The write-back step is pulled out and handed to you. Claude can change anything; only you can commit it. On a CRM the whole company runs on, that is the difference that matters.
What Claude edits in HubSpot
- Contacts and companies
- Deals, tickets, quotes, and line items
- Notes, tasks, calls, and meetings
- Custom objects and the associations between them
Workflows, lists, and Marketing Hub assets stay where they are, and emails are pulled for context but stay read-only. For the full picture, see Scratch for HubSpot.
Questions people ask
Is this an MCP server or a HubSpot app?
No. An MCP or app gives Claude the write button straight to your CRM. Scratch does not. Claude gets the same access, but writing back is a separate step you approve, one record at a time.
Will Claude touch my workflows or lists?
No. Workflows, lists, and Marketing Hub assets are never exposed for editing, and emails are pulled read-only. Claude edits records and the associations between them.
Will editing records fire my automations?
Edits in the local copy fire nothing. When you approve a record, Scratch writes it back like any CRM update, so a workflow watching that field can fire, the same as if you had edited the record by hand. The difference is that you choose which records write back, instead of one bulk pass tripping every workflow at once.
Can I undo a change after it writes back?
Yes. Every written record is reversible from Scratch, per row. The original sits next to the rewrite until you decide which one stays.
Why not just bulk-edit with an import or a script?
A CSV import and a custom script both write straight to the live CRM with no diff and no per-record approval, and a find-and-replace only does exactly what you spelled out. Scratch puts an agent on the edit, so it handles the messy cases a rule cannot, and holds every change as a word-level diff you approve before anything ships.
Can it handle the whole CRM at once?
Yes, that is the use case. Pull a few hundred records to feel the flow, then pull the whole object. Cowork and Code are built for CRM-scale jobs.
Do I need to be technical?
No. Install Scratch, connect HubSpot, point Claude at the folder, and approve the diffs.
See it on your own CRM
The fastest way to trust it is to watch it run on your records. See it run on your HubSpot CRM →, or download Scratch free and run the first pass yourself.