Skip to main content
Connect Cursor to your organization’s gateway. The wizard configures its MCP servers and Skills.

​
Run setup

With Cursor installed, install the setup tool, then run:
Sign in to your organization, choose any MCP servers or Skills you need, then review and approve the changes. You can skip MCP servers and Skills. See the overview for the shared wizard walkthrough.
Cursor setup review showing selected MCP servers and Agent Skills

Review the MCP servers and Skills the wizard will configure for Cursor.

​
Connect models in Cursor

The wizard configures MCP servers and Skills. Complete the model connection inside Cursor:
  1. Ask your administrator for the gateway base URL and a Cursor-compatible Virtual Model slug.
  2. Run tfy-local-ai-setup token in your terminal to retrieve your TrueFoundry token.
  3. Open Cursor Settings → Models → API Keys. Enter the token as the OpenAI API Key and set OpenAI Base URL to {GATEWAY_BASE_URL}/cursor/v1. Replace the placeholder with your gateway base URL and turn the API key toggle on.
  4. Add the Virtual Model slug as a custom model, then select it in a new chat.
The slug must not contain anthropic, claude, openai, gpt, gemini, or vertex. Ask your administrator for a compatible slug; see Cursor model naming rules.

​
Optional: authorize MCP servers

Authorize any selected servers that require sign-in inside Cursor. See Connect MCP from your IDE.

​
Verify the connection

Select your configured model in a new conversation and ask: Reply exactly TFY-CHAT-OK. Do not use tools. Confirm that a response arrives without an authentication or model error. Then verify the request in the gateway. For manual configuration and advanced options, see the Cursor integration guide.