Mopinion for AI agents
Mopinion captures user feedback across websites and apps, turning it into reports and analytics to improve digital experience and conversion rates. 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 Mopinion.
Pull feedback from a dataset
Retrieve recent feedback entries from a dataset to summarize customer sentiment, read-only.
Check a report's field breakdown
Look up a report's fields and results to answer a question about a specific metric.
Review a deployment's setup
Check a feedback deployment's configuration before it is referenced in an analysis.
11 Mopinion actions, graded by risk.
Every Mopinion action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
11Look things up. Allowed by default.
- mopinion.get_rootGet API Root
- mopinion.get_accountGet Account
- mopinion.get_deploymentsGet Deployments
- mopinion.get_report_by_idGet Report By ID
- mopinion.get_dataset_by_idGet Dataset by ID
- mopinion.get_report_fieldsGet Report Fields
- mopinion.get_dataset_fieldsGet Dataset Field Definitions
- mopinion.get_report_feedbackGet Report Feedback
- mopinion.get_dataset_feedbackGet Dataset Feedback
- mopinion.get_deployment_by_idGet Deployment by ID
- mopinion.get_dataset_feedback_by_idGet Dataset Feedback By ID
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Mopinion in three steps.
- 01Your users connect MopinionThey add their Mopinion api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Mopinion through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mopinion', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mopinion connects.
Users add their Mopinion 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 Mopinion 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 Mopinion from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Mopinion and Arc0, answered.
Can I use Mopinion with Claude, ChatGPT or Cursor?
Yes. Connect Mopinion 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 Mopinion actions you allow.
How do users connect Mopinion?
Users add their Mopinion 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 Mopinion actions can my agent take?
11 in total: 11 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Mopinion?
Yes. Allow read actions and deny writes in the Mopinion policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Mopinion too?
Yes. The same Mopinion connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mopinion into your agent.
Your users connect Mopinion once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan