We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

FastGPU

MCP server by FastGPU

Compare live cloud GPU rental prices and match a workload to the cheapest GPU configuration.

No sign-in (No account or key needed)Streamable HTTP

Connect to FastGPU

No sign-in needed. Connect with FastGPU’s own URL:

https://fastgpu.co/api/mcp

Paste it into any client that supports remote MCP servers. Your client talks to FastGPU directly, not through mcp.tc.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/fastgpu

About

FastGPU gives an assistant access to a live price feed of cloud GPU rentals across marketplaces, neoclouds and hyperscalers such as RunPod, Vast.ai, Lambda and AWS. It lists the cheapest on-demand price per GPU model and ranks GPU configurations for a described workload, such as serving or fine-tuning an open-weight model.

It runs as a hosted streamable HTTP endpoint at https://fastgpu.co/api/mcp. No sign-in or API key is needed. Both tools are read-only.

What you can do

  • List the cheapest live on-demand price per GPU model in USD per GPU-hour
  • See which provider offers each price and how many providers rent the GPU
  • Filter prices by vendor and tier
  • Match a workload or open-weight model to up to eight ranked GPU configurations
  • Get the VRAM a job needs and the effective hourly cost of the configuration
  • Compare the top match with a hyperscaler option when one can run the job

Tools 2

  • list_gpu_pricesRead-only

    List the cheapest live on-demand rental price per GPU model, with provider and provider count.

  • match_workloadRead-only

    Rank up to eight GPU configurations that can run a described workload at the lowest live price.

Read from the live server on 18 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.

Example prompts

  • What is the cheapest H100 to rent right now?

  • Where can I run Qwen3 32B fine-tuning at the lowest hourly cost?

  • List current GPU rental prices for AMD GPUs.

  • Which GPU do I need to serve a 70B model and what will it cost per hour?

Set up

Every client connects to fastgpu.co. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http fastgpu https://fastgpu.co/api/mcp
  1. Start Claude Code and type /mcp. fastgpu 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 FastGPU and paste this URL:
https://fastgpu.co/api/mcp
  1. 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:
  1. Check that the URL reads https://fastgpu.co/api/mcp and click Add.
  2. 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://fastgpu.co/api/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

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

mcp.json
{
  "mcpServers": {
    "fastgpu": {
      "url": "https://fastgpu.co/api/mcp"
    }
  }
}

VS Code

Or from a terminal:

code --add-mcp '{"name":"fastgpu","type":"http","url":"https://fastgpu.co/api/mcp"}'

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

.vscode/mcp.json
{
  "servers": {
    "fastgpu": {
      "type": "http",
      "url": "https://fastgpu.co/api/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
{
  "mcpServers": {
    "fastgpu": {
      "serverUrl": "https://fastgpu.co/api/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade.

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

Codex

codex mcp add fastgpu --url https://fastgpu.co/api/mcp

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

config.toml
[mcp_servers.fastgpu]
url = "https://fastgpu.co/api/mcp"

Gemini CLI

gemini mcp add --transport http fastgpu https://fastgpu.co/api/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.

{
  "mcpServers": {
    "fastgpu": {
      "type": "http",
      "url": "https://fastgpu.co/api/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://fastgpu.co/api/mcp.

Embed

Show FastGPU in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![FastGPU on mcp.tc](https://mcp.tc/i/fastgpu/badge.svg)](https://mcp.tc/i/fastgpu)
HTML
<a href="https://mcp.tc/i/fastgpu"><img src="https://mcp.tc/i/fastgpu/badge.svg" alt="FastGPU on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/fastgpu.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/fastgpu" title="FastGPU on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/fastgpu.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the FastGPU card to your site.

Markdown
Add the mcp.tc card for FastGPU, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/fastgpu.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="fastgpu"><a href="https://mcp.tc/i/fastgpu">FastGPU on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![FastGPU on mcp.tc](https://mcp.tc/i/fastgpu/badge.svg)](https://mcp.tc/i/fastgpu)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 02:38 UTC.

Follow FastGPU and we’ll email you when something changes.

  1. , Automatic check

    1 tool changed.

    Details, 8 Nov 2026, 11:50 UTC

    Changed 1

    • match_workloadinput schema and output schema
      • New parameters: concurrency context_tokens active_params_b engram_placement
  2. , Automatic check

    1 tool changed.

    Details, 29 Oct 2026, 17:47 UTC

    Changed 1

    • match_workloadoutput schema
  3. , Automatic check

    1 tool changed.

    Details, 28 Oct 2026, 17:47 UTC

    Changed 1

    • match_workloaddescription
      Before

      Ranks up to eight GPU configurations that can run a job at the lowest live price. Describe the job in query (an open-weight model to serve or fine-tune, a model size, or a GPU need) or with the structured fields. Each match gives the GPU count, the USD per hour for the whole configuration and a one-line reason; the answer also states the VRAM the job needs and how much cheaper the top match is than a hyperscaler running the same job. Use it to decide where to run a workload; use list_gpu_prices for the price of a named GPU. Open-weight models only: an API-only model such as GPT-4 returns no matches and a note. Between otherwise equal offers, a small disclosed tie-break favors providers that pay FastGPU a referral (each match reports partner). Hard limits (budget_usd_hr, max_total_usd with duration_hours, max_quote_age_minutes) drop every configuration that breaks them; limits reports what was dropped. Read-only: it does not rent or launch GPUs. No key required.

      After

      Ranks up to eight GPU configurations that can run a job at the lowest live price. Describe the job in query (an open-weight model to serve or fine-tune, a model size, or a GPU need) or with the structured fields. Each match gives the GPU count, the USD per hour for the whole configuration and a one-line reason; the answer also states the VRAM the job needs and how much cheaper the top match is than a hyperscaler running the same job. Use it to decide where to run a workload; use list_gpu_prices for the price of a named GPU. Open-weight models only: an API-only model such as GPT-4 returns no matches and a note. Ranked on price and fit alone: no provider pays for placement (each match still reports partner, a provider that pays FastGPU a referral). Hard limits (budget_usd_hr, max_total_usd with duration_hours, max_quote_age_minutes) drop every configuration that breaks them; limits reports what was dropped. Read-only: it does not rent, reserve or launch GPUs. No key required.

  4. , Automatic check

    2 tools changed.

    Details, 18 Oct 2026, 01:42 UTC

    Changed 2

    • list_gpu_pricesinput schema
      • Description of vendor
        Before

        Filter by GPU vendor.

        After

        Return only GPUs made by this vendor (case-insensitive). Combines with tier: both must match. Omit for every vendor.

      • Description of tier
        Before

        Filter by tier.

        After

        Return only one class of GPU (case-insensitive; combines with vendor). flagship: the current top training and inference accelerators (H100, H200, B200, GB200, MI300X, MI355X). datacenter: earlier or…

    • match_workloaddescription
      Before

      Describe a job (an open-weight model to serve or fine-tune, a model size, or a GPU need) and get up to eight ranked GPU configurations that can run it at the lowest live price, each with the GPU count, the effective USD per hour for the whole configuration, and a one-line reason; the result also states the VRAM the job needs and, when a hyperscaler can run the same job, which one and what percent cheaper the top match is. Use it when the user asks where to run a workload or which GPU they need, rather than the price of a named GPU. It sizes open-weight models only: an API-only model such as GPT-4 returns no matches and a note. Results mirror FastGPU's website and apply a small, disclosed tie-break toward providers that pay FastGPU a referral, only between otherwise equal offers (each match reports partner true/false). Optional hard limits (budget_usd_hr, max_total_usd with duration_hours, max_quote_age_minutes) leave out every configuration that breaks them, and limits reports what wa…

      After

      Ranks up to eight GPU configurations that can run a job at the lowest live price. Describe the job in query (an open-weight model to serve or fine-tune, a model size, or a GPU need) or with the structured fields. Each match gives the GPU count, the USD per hour for the whole configuration and a one-line reason; the answer also states the VRAM the job needs and how much cheaper the top match is than a hyperscaler running the same job. Use it to decide where to run a workload; use list_gpu_prices for the price of a named GPU. Open-weight models only: an API-only model such as GPT-4 returns no matches and a note. Between otherwise equal offers, a small disclosed tie-break favors providers that pay FastGPU a referral (each match reports partner). Hard limits (budget_usd_hr, max_total_usd with duration_hours, max_quote_age_minutes) drop every configuration that breaks them; limits reports what was dropped. Read-only: it does not rent or launch GPUs. No key required.

  5. , Automatic check

    Tracking started: 2 tools.

FAQ

Can I paste mcp.tc/i/fastgpu into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://fastgpu.co/api/mcp, so your client talks to FastGPU directly. The quick link is for sharing: it opens this page, with setup steps for every client.

Does FastGPU need an API key or a sign-in?

No. FastGPU doesn’t ask for an account or key.

Is FastGPU a remote or a local server?

Remote. FastGPU hosts it at https://fastgpu.co/api/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can FastGPU do?

It has 2 tools: list_gpu_prices and match_workload. You can list the cheapest live on-demand price per GPU model in USD per GPU-hour, see which provider offers each price and how many providers rent the GPU and filter prices by vendor and tier.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to FastGPU?

Yes. FastGPU’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read FastGPU’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with FastGPU. This page was built from FastGPU’s public metadata, last checked on 18 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.