Refiner for AI agents
Refiner collects in-product surveys and feedback, letting teams track contacts, segments, and survey responses to understand users. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Refiner.
Pull survey responses
Get the latest survey responses and reporting for a form to summarize what customers are saying.
Update a contact record
Update a contact's fields after a support conversation reveals new information about them.
Confirm before deleting a contact
Look up a contact's segment and history first, then delete them only once approved.
10 Refiner actions, graded by risk.
Every Refiner action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- refiner.get_formsGet Forms
- refiner.get_contactGet Contact
- refiner.get_contactsGet Contacts
- refiner.get_segmentsGet Segments
- refiner.get_reportingGet Reporting
- refiner.get_responsesGet Survey Responses
- refiner.get_account_infoGet Account Info
- refiner.track_eventTrack Event
write
1Create and change things. Allow, or ask the user first.
- refiner.update_contactUpdate Contact
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- refiner.delete_contactDelete Contact
Refiner in three steps.
- 01Your users connect RefinerThey add their Refiner api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “update Contact” can wait for the user, and “delete Contact” can be denied outright.
- 03Any agent can actYour agent calls Refiner through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('refiner', { read: 'allow', write: 'ask', // update_contact destructive: 'deny', // delete_contact }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Refiner connects.
Users add their Refiner api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Refiner connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Refiner from any agent.
Refiner and Arc0, answered.
Can I use Refiner with Claude, ChatGPT or Cursor?
Yes. Connect Refiner to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Refiner actions you allow.
How do users connect Refiner?
Users add their Refiner api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Refiner actions can my agent take?
10 in total: 8 read, 1 write and 1 destructive, such as “update Contact”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Refiner?
Yes. Actions like “delete Contact” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Refiner too?
Yes. The same Refiner connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Refiner into your agent.
Your users connect Refiner once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan