# Hundredth Run GPU Cloud Prices MCP server

> Compare public cloud GPU rental prices (H100, H200, B200, A100, L40S) across 20+ providers, with source links and dates.

- Listing: https://mcp.tc/i/hundredth-run-gpu-cloud-prices
- Connect: use the server's own URL `https://hundredthrun-compute-desk.pages.dev/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Data & Analytics](https://mcp.tc/c/analytics)
- Vendor: Hundredth Run
- Homepage: <https://hundredthrun-compute-desk.pages.dev>

## About

Provides public cloud GPU rental prices in USD per GPU-hour across more than 20 providers. You can list tracked GPUs with their price ranges, find the cheapest on-demand offer for a GPU model, and search the per-provider price table for on-demand, spot, preemptible or reserved rates. Each row includes the source URL and the date it was checked.

It runs as a hosted Streamable HTTP endpoint. No sign-in or API key is needed. The underlying data is published under CC BY 4.0.

## What it can do

- List tracked GPUs with min, median and max on-demand price
- Find the cheapest on-demand price for one GPU model
- Search price rows by GPU, provider and price type
- Compare spot, preemptible and reserved rates
- Get source URL and check date for every price

## Tools (3)

- `list_gpus`: List tracked cloud GPUs with on-demand price range, provider count and cheapest offer. (read-only)
- `cheapest_gpu`: Cheapest public on-demand price for one GPU model, with provider and source URL. (read-only)
- `get_prices`: Search per-provider GPU price rows by GPU, provider and price type, cheapest first. (read-only)

## Example prompts

- "What is the cheapest H100 on-demand price right now?"
- "Compare L40S prices across providers, cheapest first."
- "Show spot rates for A100 on Vast.ai."
- "List all tracked GPUs with their median price per hour."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http hundredth-run-gpu-cloud-prices https://hundredthrun-compute-desk.pages.dev/mcp
```

2. Start Claude Code and type `/mcp`. **hundredth-run-gpu-cloud-prices** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Hundredth Run GPU Cloud Prices** and paste this URL:

```url
https://hundredthrun-compute-desk.pages.dev/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Hundredth%20Run%20GPU%20Cloud%20Prices&connectorUrl=https%3A%2F%2Fhundredthrun-compute-desk.pages.dev%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://hundredthrun-compute-desk.pages.dev/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://hundredthrun-compute-desk.pages.dev/mcp` as the server URL, then for authentication choose **No authentication**.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=hundredth-run-gpu-cloud-prices&config=eyJ1cmwiOiJodHRwczovL2h1bmRyZWR0aHJ1bi1jb21wdXRlLWRlc2sucGFnZXMuZGV2L21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "hundredth-run-gpu-cloud-prices": {
      "url": "https://hundredthrun-compute-desk.pages.dev/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=hundredth-run-gpu-cloud-prices&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fhundredthrun-compute-desk.pages.dev%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"hundredth-run-gpu-cloud-prices","type":"http","url":"https://hundredthrun-compute-desk.pages.dev/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "hundredth-run-gpu-cloud-prices": {
      "type": "http",
      "url": "https://hundredthrun-compute-desk.pages.dev/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "hundredth-run-gpu-cloud-prices": {
      "serverUrl": "https://hundredthrun-compute-desk.pages.dev/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add hundredth-run-gpu-cloud-prices --url https://hundredthrun-compute-desk.pages.dev/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.hundredth-run-gpu-cloud-prices]
url = "https://hundredthrun-compute-desk.pages.dev/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http hundredth-run-gpu-cloud-prices https://hundredthrun-compute-desk.pages.dev/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "hundredth-run-gpu-cloud-prices": {
      "type": "http",
      "url": "https://hundredthrun-compute-desk.pages.dev/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://hundredthrun-compute-desk.pages.dev/mcp`.

## Recent changes

- 2026-11-14 20:23 UTC: Tracking started: 3 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/hundredth-run-gpu-cloud-prices#history (Atom feed: https://mcp.tc/i/hundredth-run-gpu-cloud-prices/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1.0.0
- MCP protocol version: 2025-06-18
- Last checked: 2026-11-15 (reachable)
- Listed: 2026-11-14
- Updated: 2026-11-14

---
Source: https://mcp.tc/i/hundredth-run-gpu-cloud-prices (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report