Chatfai for AI agents
ChatFAI lets people have AI-driven conversations with fictional characters from movies and games, built for entertainment rather than business workflows. 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 Chatfai.
Search for a character
Search for a fictional character by name before starting a conversation with them.
Look up a character's profile
Look up a public character's profile details before referencing them in content.
Check existing conversations
List existing conversations to pick up where one left off instead of starting over.
3 Chatfai actions, graded by risk.
Every Chatfai action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- chatfai.search_charactersSearch Characters
- chatfai.get_public_character_by_idGet Public Character By ID
- chatfai.list_chatfai_conversationsList Conversations
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.
Chatfai in three steps.
- 01Your users connect ChatfaiThey add their Chatfai 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 Chatfai through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('chatfai', { 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 Chatfai connects.
Users add their Chatfai 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 Chatfai 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 Chatfai from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Chatfai and Arc0, answered.
Can I use Chatfai with Claude, ChatGPT or Cursor?
Yes. Connect Chatfai 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 Chatfai actions you allow.
How do users connect Chatfai?
Users add their Chatfai 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 Chatfai actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Chatfai?
Yes. Allow read actions and deny writes in the Chatfai policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Chatfai too?
Yes. The same Chatfai connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Chatfai into your agent.
Your users connect Chatfai once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan