Entelligence for AI agents
Entelligence uses AI to answer questions about a codebase, giving teams a repository agent for insights and recommendations that speed up onboarding and code review. 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 Entelligence.
Ask the repo agent a question
Ask the repository agent how a specific module works before making a change to it.
Add a repository for indexing
Add a new repository so the agent can start answering questions about its code.
Read-only code exploration
Keep repository questions read-only, since the agent explains code without changing it.
2 Entelligence actions, graded by risk.
Every Entelligence 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
2Create and change things. Allow, or ask the user first.
- entelligence.add_a_new_repositoryAdd a new repository
- entelligence.interact_with_the_repository_agentInteract with the repository agent
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Entelligence in three steps.
- 01Your users connect EntelligenceThey add their Entelligence no auth on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “add a new repository” can wait for the user to approve.
- 03Any agent can actYour agent calls Entelligence through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('entelligence', { read: 'allow', write: 'ask', // add_a_new_repository destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Entelligence connects.
Entelligence needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
The same Entelligence 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
- No auth
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Entelligence from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Entelligence and Arc0, answered.
Can I use Entelligence with Claude, ChatGPT or Cursor?
Yes. Connect Entelligence 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 Entelligence actions you allow.
How do users connect Entelligence?
Entelligence needs no credentials. Arc0 still applies your policies and records every call, so public tools get the same controls as private ones.
Which Entelligence actions can my agent take?
2 in total: 0 read, 2 write and 0 destructive, such as “add a new repository”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Entelligence?
Yes. Allow read actions and deny writes in the Entelligence policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Entelligence too?
Yes. The same Entelligence connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Entelligence into your agent.
Your users connect Entelligence once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan