Skip to main content
nexus cursor configures Cursor IDE. Cursor CLI (agent or cursor-agent) is not supported. Preview OpenAI Chat Completions Nexus Auto with Provider Keys

Quick start

Install and sign in

You need Node.js 22 or later, git, and bash. On Windows, run the installer from Git Bash. PowerShell breaks the script’s line endings.
Sign in with your browser, or paste a Fireworks API key (fw_...).Already set up? Skip to step 2.

Quit Cursor IDE

Fully quit Cursor IDE before you connect or run off. A running Cursor IDE overwrites the change from memory. If it’s open, Nexus CLI waits until you quit. --force writes anyway, which isn’t recommended.

Connect Cursor IDE

Nexus CLI registers the Fireworks catalog in the picker and points every mode you already have in modelConfig at the default model. It never adds modes.

Reopen and pick a model

Reopen Cursor IDE and choose a Fireworks model. The default is nexus/auto. To change the default for every mode, run nexus cursor --model glm-latest.
Cursor IDE model picker showing Auto selected with Fireworks DeepSeek, GLM, Kimi, and MiniMax models

Cursor IDE after Nexus CLI, with Auto selected

nexus cursor status shows the provider, where the key comes from, and the configured model.
While connected, only Fireworks models work. Cursor IDE’s built-in models are hidden until you run off. Cursor IDE also enforces a server-side allowlist, so not every Fireworks model is selectable. Some features may still use Cursor’s own backend, depending on plan and version.

Use Nexus Auto

Nexus CLI registers Nexus Auto in Cursor IDE as nexus/auto, because Cursor reserves the bare auto name for its own router.
  • Anthropic and OpenAI model turns: connect a Provider Key. Cursor IDE can’t send extra headers, so Nexus CLI doesn’t send keys saved with nexus auto, and manual setup can’t add them either. Without a Provider Key, Nexus Auto serves every turn with open models.
  • Provider scope: nexus auto --providers has no effect in Cursor IDE.

MCP and tools

Nexus CLI doesn’t touch MCP. Set up servers in Cursor IDE as usual. Nexus CLI does not add web search to Cursor IDE. See Web Search.

Microsoft Foundry

Nexus CLI can connect Cursor IDE to Fireworks models deployed in your Azure subscription. See Nexus for Microsoft Foundry. Nexus Auto is not available on Foundry.

Troubleshooting

  • Model name is not valid: "auto", or the same error for another Fireworks ID: Cursor IDE stopped sending your Fireworks key. Cursor can turn the key off after Fireworks rejects a request, such as when the key is revoked or a model ID is not found. Without a key, Cursor treats Fireworks IDs as unknown models. Open Settings → Models, turn OpenAI API Key back on, and retry.
  • The key was revoked: turning it back on is not enough. Run nexus login --force for a new key, fully quit Cursor IDE, and run nexus cursor. With manual setup, paste a new key from Fireworks settings.
See Nexus Auto for issues that affect every harness.

Manual setup (advanced)

Open model settings

In Cursor IDE, open Settings, then Models.

Add your Fireworks key

Under API Keys, paste your Fireworks key into OpenAI API Key. Turn on Override OpenAI Base URL and enter https://api.fireworks.ai/inference/v1.

Add a model

Add a custom model with a Fireworks ID, such as glm-latest, then select it in chat.
See what changes without the Nexus CLI.

What the Nexus CLI writes

Cursor IDE stores AI settings in SQLite, in User/globalStorage/state.vscdb under ~/.config/Cursor (Linux), ~/Library/Application Support/Cursor (macOS), or %APPDATA%\Cursor (Windows):On Linux, encryption needs libsecret. Without it, Cursor IDE only obfuscates the key and Nexus CLI warns you.off restores your previous AI settings and key from the snapshot under ~/.nexus/cursor/. Without a snapshot, it removes only what Nexus CLI added. Use --db-path for a non-default state.vscdb.