Faceup for AI agents
FaceUp is an anonymous reporting tool for companies and schools, letting employees and students safely report issues and misconduct without fear of retaliation. 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 Faceup.
Pull reporting statistics
Query aggregate statistics on submitted reports to summarize trends for a compliance review.
Read-only statistics access
Keep every statistics query read-only, since the connection has no way to alter a submitted report.
Track resolution trends over time
Compare statistics across time periods to see whether reported issues are being resolved faster.
1 Faceup actions, graded by risk.
Every Faceup action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
1Create and change things. Allow, or ask the user first.
- faceup.graphql_statistics_queryFaceUp GraphQL Statistics Query
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Faceup in three steps.
- 01Your users connect FaceupThey add their Faceup api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “faceUp GraphQL Statistics Query” can wait for the user to approve.
- 03Any agent can actYour agent calls Faceup through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('faceup', { read: 'allow', write: 'ask', // graphql_statistics_query destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Faceup connects.
Users add their Faceup 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 Faceup 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 Faceup from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Faceup and Arc0, answered.
Can I use Faceup with Claude, ChatGPT or Cursor?
Yes. Connect Faceup 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 Faceup actions you allow.
How do users connect Faceup?
Users add their Faceup 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 Faceup actions can my agent take?
1 in total: 0 read, 1 write and 0 destructive, such as “faceUp GraphQL Statistics Query”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Faceup?
Yes. Allow read actions and deny writes in the Faceup policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Faceup too?
Yes. The same Faceup connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Faceup into your agent.
Your users connect Faceup once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan