Cursor for AI agents
Cursor is an AI-powered code editor built on VSCode, and its API exposes cloud agent activity, analytics, and code tracking for a team's engineering work. 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 Cursor.
Check a cloud agent's conversation
Check a cloud agent's conversation to review what changes it made and why.
List active agents
List running agents across the team before assigning a new coding task.
Check connected repositories
List available GitHub repositories before pointing a new cloud agent at one.
5 Cursor actions, graded by risk.
Every Cursor action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- cursor.get_meGet API Key Info
- cursor.list_agentsList Agents
- cursor.list_modelsList Available Models
- cursor.list_repositoriesList GitHub Repositories
- cursor.get_agent_conversationGet Agent Conversation
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.
Cursor in three steps.
- 01Your users connect CursorThey add their Cursor 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 Cursor through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('cursor', { 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 Cursor connects.
Users add their Cursor 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 Cursor 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 Cursor from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Cursor and Arc0, answered.
Can I use Cursor with Claude, ChatGPT or Cursor?
Yes. Connect Cursor 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 Cursor actions you allow.
How do users connect Cursor?
Users add their Cursor 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 Cursor actions can my agent take?
5 in total: 5 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Cursor?
Yes. Allow read actions and deny writes in the Cursor policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Cursor too?
Yes. The same Cursor connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Cursor into your agent.
Your users connect Cursor once, under your brand. Your agent gets 5 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan