Eden AI for AI agents
Eden AI is a single API for orchestrating AI models from multiple providers, covering text, image, audio, and document tasks. 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 Eden AI.
Run a chat completion
Send a prompt through a chosen model to generate a response for a user's request.
Moderate generated text
Run text moderation on a draft before it is shown to a customer, to catch flagged content.
Check cost overview first
Read the cost overview as a check before running a large batch job across multiple models.
10 Eden AI actions, graded by risk.
Every Eden AI 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.
- eden_ai.get_responseGet Response
- eden_ai.get_cost_overviewGet Cost Overview
- eden_ai.count_anthropic_tokensCount Anthropic Tokens
write
7Create and change things. Allow, or ask the user first.
- eden_ai.create_responseCreate Response
- eden_ai.create_embeddingsCreate Embeddings
- eden_ai.create_chat_completionCreate Chat Completion
- eden_ai.create_anthropic_messageCreate Anthropic Message
- eden_ai.moderate_textModerate Text
- eden_ai.run_universal_aiRun Universal AI
- eden_ai.discover_capabilitiesDiscover AI Capabilities
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Eden AI in three steps.
- 01Your users connect Eden AIThey add their Eden AI 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 Eden AI through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('eden_ai', { 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 Eden AI connects.
Users add their Eden AI 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 Eden AI 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 Eden AI from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Eden AI and Arc0, answered.
Can I use Eden AI with Claude, ChatGPT or Cursor?
Yes. Connect Eden AI 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 Eden AI actions you allow.
How do users connect Eden AI?
Users add their Eden AI 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 Eden AI actions can my agent take?
10 in total: 3 read, 7 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 Eden AI?
Yes. Allow read actions and deny writes in the Eden AI policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Eden AI too?
Yes. The same Eden AI connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Eden AI into your agent.
Your users connect Eden AI 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