Skip to main content
Replicas supports Cursor as a first-class coding agent alongside Claude Code and Codex. Cursor chats run inside your workspace VM through the Cursor Agent SDK, with the same repository access, environment configuration, and integrations as other agents.

​
Setup

Cursor uses an API key. There is no OAuth flow like Claude Code or Codex.
  1. Generate a user API key from Cursor Dashboard → Integrations, or a service account API key from Team Settings if your org uses Cursor Enterprise.
  2. Paste the key in Preferences → Organization → Coding Agents during onboarding or anytime later.
  3. Set org-level credentials for the whole team, or add a personal key in Account settings (Preferences → Account) that takes priority over org defaults.
See Credentials for scope details (organization vs user) and auth retry behavior.
User API keys bill to that user’s Cursor plan. Service account keys bill to the team that owns the service account.

​
Models

Cursor proxies many underlying models (Composer, Claude, GPT, Gemini, Grok, and more). The models available in Replicas depend on whether your organization has a connected Cursor API key. When an organization Cursor API key is connected, Replicas loads the live model catalog from Cursor and lets admins enable any returned model ID in Preferences → Organization → Coding Agents → Cursor → Models. The checklist is searchable and paginated so large Cursor catalogs stay manageable. If no organization Cursor API key is connected, Replicas falls back to its default Cursor model list. See Credentials for organization and personal key behavior. Set the org default model under Preferences → Organization → Settings → Defaults. Each workspace remembers the model used on its Cursor chat tab.

​
Using Cursor in Workspaces

Every workspace can have multiple chats, one per agent. Open the Cursor chat tab to start or continue a Cursor session. Cursor agents can:
  • Read and edit files in the cloned repository
  • Run shell commands in the workspace VM
  • Create branches, commits, and pull requests
  • Attach and interpret images in the composer (screenshots, diagrams)
  • Use Plan Mode to propose a plan before changing code
Cursor does not support Fast Mode or Codex goal mode (/goal). The composer uses the selected model directly without a separate fast tier.

​
Plan Mode

Start a message with /plan or toggle plan mode in the composer. Cursor runs in plan mode and returns a structured plan you can review in the Canvas tab before asking it to implement.

​
Chat history

Cursor chat history persists across turns and survives workspace sleep. Use replicas read from the CLI to inspect transcript history from your terminal.

​
Programmatic Use

Select Cursor anywhere Replicas accepts a coding agent:
SurfaceHow to choose Cursor
CLI-a cursor on replicas create and replicas send
API"coding_agent": "cursor" on create and message requests
MCP"coding_agent": "cursor" on create_replica and send_replica_message
AutomationsSet Coding agent to Cursor in the automation editor
Slack, Linear, GitHub, GitLabSet Cursor as the default coding agent
Example CLI: 
replicas create fix-layout \
  -e frontend \
  -a cursor \
  -m "Fix the responsive layout on the settings page"
Example API: 
curl -X POST "https://api.tryreplicas.com/v1/replica" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "fix-layout",
    "environment_id": "ENVIRONMENT_UUID",
    "message": "Fix the responsive layout on the settings page",
    "coding_agent": "cursor",
    "model": "composer-2.5"
  }'

​
When to Use Cursor

Cursor is a strong fit when:
  • Your team already uses Cursor and has API access configured
  • You want Composer’s agent loop for multi-file edits and terminal work
  • You prefer API-key auth over OAuth for automated or shared workflows (especially with service accounts)
Claude Code and Codex remain better choices when you need provider-specific features like Claude background tasks, Codex goal mode, or MCP transports that Cursor does not load (see Environments → MCPs).