compute.pangle.online — GPU compute meta-aggregator

MCP serverDev tools

This connects your AI to a live GPU rental market with over 2,500 offers from a dozen providers. Your AI can compare current prices, look at how they have moved over time, and set watches or limit orders so you catch the deal you want.

Use compute.pangle.online — GPU compute meta-aggregator in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add compute.pangle.online — GPU compute meta-aggregator and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use compute.pangle.online to search offers

Details

Available today. Use it from your connected AI after setup.

After adding it, ask your AI to show the current GPU rental offers or set a watch on a price you are targeting.

compute.pangle.online — GPU compute meta-aggregatorStart free

What your AI can do with it

  • Compare 2,500+ live GPU rental offers across a dozen providers
  • Look up price history to see how rental costs have changed
  • Watch specific offers so you can follow their price over time
  • Set limit orders at the price you are willing to pay
  • Find the lowest-priced GPU rental that fits what you need

Install compute.pangle.online — GPU compute meta-aggregator

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user compute-pangle-online-gpu-comput 'https://compute.pangle.online/mcp/'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://compute.pangle.online/mcp/

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=compute-pangle-online-gpu-comput&config=eyJ1cmwiOiJodHRwczovL2NvbXB1dGUucGFuZ2xlLm9ubGluZS9tY3AvIn0=

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://compute.pangle.online/mcp/

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add compute-pangle-online-gpu-comput --url 'https://compute.pangle.online/mcp/'

    Run it once, then sign in with codex mcp login compute-pangle-online-gpu-comput if the server asks for an account.

From the project's README

As published by aitools420/compute-wick in README.md.

One process: provider pollers + SQLite store + ranked REST API + MCP server + the site. Live at https://compute.pangle.online · API /api/offers, /api/history, /api/idle-history, /api/watches · MCP /mcp/ (streamable HTTP).

Run anywhere (the VPS lift)

docker compose up          # or:
python3 -m venv venv && venv/bin/pip install -r requirements.txt
venv/bin/uvicorn app:app --port 8956

No external services, no keys required (keys in .env deepen Vast/RunPod results; DataCrunch and Akash need none).

The fee levers — there are two, and confusing them corrupts the data

FEE_BPS (core/economics.py) marks up displayed prices, and it is 0, permanently. The book, the tape, the index and the per-chip prices are published as THE MARKET's numbers — check any of them against the provider's own page. A markup here would quietly make every published price ours instead of theirs, so this lever stays off.

EXEC_FEE_BPS is the platform fee, charged on what we settle, never on what the provider charges: 2.5%, one cent minimum, capped at $5 per lease per UTC day (core/meter.py). Renters place on their own provider key and pay the provider directly; this is the only thing we take, and it is disclosed in the quote and the receipt before anything is placed.

REF_VAST / REF_RUNPOD referral slots ride the same seam.

Layout

providers/ one drop-in module per marketplace · core/ schema, rank, economics, stats · db.py SQLite (WAL) with provider_health honesty table · app.py FastAPI + scheduler + MCP mount · web/ the hand-written site (see DESIGN-DIRECTION.md).

Tests: venv/bin/python -m tests.test_pipeline

Generated pages

web/gpu/, web/vs/ and web/sitemap.xml are built artifacts — regenerate with venv/bin/python gen_gpu_pages.py (the deployment runs it hourly).

Fonts

Martian Mono ships in web/fonts/ (SIL OFL). The display serif (Erode, by Indian Type Foundry via Fontshare) is not redistributed here — its license doesn't allow it; fetch it from https://www.fontshare.com/fonts/erode into web/fonts/ as erode-400.woff2 / erode-600.woff2, or let the stack fall back to Georgia.

License

AGPL-3.0 — see LICENSE. Run it, fork it, learn from it; if you serve a modified version, share your changes the same way.

Tools it offers (25)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • search_offers
  • get_offer
  • market_stats
  • price_history
  • idle_history
  • best_value
  • provider_reliability
  • price_position
  • spot_spread
  • will_it_fit
  • true_cost_notes
  • register_account
  • account_usage
  • create_watch
  • watch_status
  • delete_watch
  • create_limit_order
  • limit_order_status
  • cancel_limit_order
  • rent_x402
  • rent_offer
  • rent_best
  • rental_status
  • destroy_rental
  • fill_limit_order

Signals

Last commit
Aug 2026
Advanced
Delivery
gpu-rental-market MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
online-pangle-compute-gpu-rental-market
Source
github.com/aitools420/compute-wick
Hosted endpoint
https://compute.pangle.online/mcp/