CometAPI for AI agents
CometAPI is a unified gateway to generative AI models from multiple providers, letting a team call one API instead of integrating each model separately. 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 CometAPI.
Create a chat completion
Send a prompt to a chosen model and get back a chat completion response.
Check available models
List available models across providers before deciding which one fits a specific task.
Check API key usage
Check current API key usage before running a large batch of generation requests.
6 CometAPI actions, graded by risk.
Every CometAPI action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- cometapi.list_modelsList Models
- cometapi.get_api_key_usageGet API Key Usage
write
4Create and change things. Allow, or ask the user first.
- cometapi.create_responseCreate Response
- cometapi.create_embeddingsCreate Embeddings
- cometapi.create_chat_completionCreate Chat Completion
- cometapi.moderate_contentModerate Content
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
CometAPI in three steps.
- 01Your users connect CometAPIThey add their CometAPI api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Response” can wait for the user to approve.
- 03Any agent can actYour agent calls CometAPI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('cometapi', { read: 'allow', write: 'ask', // create_response destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How CometAPI connects.
Users add their CometAPI 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 CometAPI 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 CometAPI from any agent.
CometAPI and Arc0, answered.
Can I use CometAPI with Claude, ChatGPT or Cursor?
Yes. Connect CometAPI 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 CometAPI actions you allow.
How do users connect CometAPI?
Users add their CometAPI 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 CometAPI actions can my agent take?
6 in total: 2 read, 4 write and 0 destructive, such as “create Response”. Your policies decide which of them each agent may call.
Can I make my agent read-only in CometAPI?
Yes. Allow read actions and deny writes in the CometAPI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call CometAPI too?
Yes. The same CometAPI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug CometAPI into your agent.
Your users connect CometAPI once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan