# How to give Claude Code, Codex or Cursor access to GPUs (MCP setup)

> Connect one MCP server and your coding agent can estimate, launch and watch GPU jobs on your account, with dry runs and spending limits.

Source: https://www.nodus-compute.ai/blog/give-claude-code-codex-cursor-gpus-mcp/
Build revision: 142da3a7366b5a47f7dcfa3bcdfcfa0d0c5d86f2

**Short answer:** connect your coding agent to a GPU platform’s MCP server. The agent can then estimate, launch, watch and fetch results from GPU jobs from the same chat where it wrote the code. With [Nodus](https://www.nodus-compute.ai/) that is one command per client, and every paid action shows a dry run and cost estimate before it runs.

Coding agents are great at writing a training script and terrible at the part after: finding a GPU, shipping code to it, watching logs, copying results back. MCP closes that loop.

## Claude Code

Terminal window

```sh
claude mcp add --scope user --transport http nodus https://api-next.nodus-compute.ai/mcp
```

Then run `/mcp`, pick `nodus`, and sign in in your browser.

## Codex

Terminal window

```sh
codex mcp add nodus --url https://api-next.nodus-compute.ai/mcp
codex mcp login nodus
```

## Cursor

Add this to `~/.cursor/mcp.json`:

```json
{
  "mcpServers": {
    "nodus": { "type": "http", "url": "https://api-next.nodus-compute.ai/mcp" }
  }
}
```

## Any other MCP client

Add a remote HTTP MCP server with URL `https://api-next.nodus-compute.ai/mcp` and follow the sign-in prompt. Prefer a local server? Install the CLI and run `nodus mcp install`, which configures the agents on your machine.

## Verify without spending money

Ask the agent: “List my Nodus jobs.” That is read only. A good first prompt for any agent that can read URLs:

```text
Read https://nodus-compute.ai/connect.md and help me connect Nodus to this agent.
Verify setup by listing my jobs. Do not start paid compute.
```

## What the agent can actually do

The server exposes generic tools over every resource: `get`, `describe`, `logs`, `estimate`, `apply`, `exec` and more. In practice that means prompts like:

* “Run train.py on a 24 GB GPU with a $5 cap and stream the logs.”
* “Why did job/train fail?”
* “Fine-tune Qwen3 0.6B with LoRA on chats.jsonl and download the adapter.”
* “What did my sandboxes cost this week?”

## Guardrails that matter when an agent holds your credit card

* **Writes are dry-run first.** The agent sees the object as it would be created plus the cost estimate, and it only runs once confirmed.
* **Same limits as you.** The agent uses your account, projects, budgets and spending caps. A project budget stops it from overspending even if it gets creative.
* **Hard caps per job.** `maxCostUSD` stops a job gracefully, with a checkpoint, before it passes the cap.
* **Frozen rates.** The hourly rate is fixed when the machine is chosen and holds for the whole run.

## FAQ

**Do I need a separate “agents” product to use Claude Code with GPUs?** No. MCP is enough. Nodus Agents is a different feature for running agent conversations inside Nodus.

**Which GPU does the agent get?** By default the cheapest offering that fits the request and can start now, within your limits. You can ask for a specific type like H100 or B200.

**What does it cost to try?** New accounts get a $30 starter grant, no card needed for the first runs.

Setup for every client: [nodus-compute.ai/connect](https://www.nodus-compute.ai/connect/)