Skip to content
MCP server

Lantern Works GPU Prices: daily GPU rental price comparison

Daily-checked GPU rental prices with receipts, price changes and stack cost estimates

Install
Pricing
Free
Platforms
API, CLI
Runs
Locally or Remotely
Version
0.6.0
Listing updated
5 days ago

Similar MCP servers

About Lantern Works GPU Prices: daily GPU rental price comparison

Lantern Works GPU Prices: daily GPU rental price comparison is a free MCP server for cloud and infrastructure. It can run locally on your machine or as a hosted remote server.

Every price carries its evidence. The tracker covers 31 GPU models across 26 vendors, 173 rates in the feed seen, each read from the vendor's own pricing page with its source URL, a quoted snippet and a checked-at time, so an agent can verify before acting.

The local package has nine read-only tools. Four are about GPUs and cost: compare_gpu_prices, get_price_changes, estimate_job_cost and optimize_stack. optimize_agent_stack picks the cheapest cited option per component from a plain-text description of an agent. search_deals, compare_deals, get_deal and rebuild_quote cover a deal catalogue of 202 offers. The hosted endpoint adds four price-watch tools, create_watch_key, watch_price, list_watches and delete_watch.

It installs with uvx from PyPI or connects remotely, needs no key, and a standard-library Python script produces a first quote. Deal rows mark referral links with an affiliate flag, which the site says does not affect ranking.

Install

Run in a terminal

claude mcp add --transport http lantern-works-deals 'https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry'

Add to Settings → Connectors → Add custom connector

https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "lantern-works-deals": {
      "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "lantern-works-deals": {
      "type": "http",
      "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "lantern-works-deals": {
      "serverUrl": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}

Add to Grok Bot desktop app → Connect apps → Add a custom connector

https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry

Enter a Name (for example "Lantern Works GPU Prices: daily GPU rental price comparison"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "lantern-works-deals": {
      "type": "http",
      "url": "https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • LANTERN_DEALS_FILEOptional path to a local deals.json (offline use).
  • LANTERN_GPU_PRICES_FILEOptional path to a local gpu-prices.json (offline use).

Tools this server provides (13)

Taken from the project documentation; the running server may differ.

compare_gpu_prices
Hourly rental prices for a GPU model across tracked providers, cheapest first.
get_price_changes
GPU price moves among tracked providers, newest first.
optimize_stack
Cheapest tracked plan per usage line, with sources.
optimize_agent_stack
Cheapest cited option per component from a plain-text agent description.
estimate_job_cost
Cost of one GPU job among tracked providers, cheapest first.
search_deals
Searches the deal catalogue.
compare_deals
Compares deals.
get_deal
Returns one deal.
rebuild_quote
Rebuilds a price quote.
create_watch_key
Hosted only: creates a key for price watches.
watch_price
Hosted only: watches a price.
list_watches
Hosted only: lists watches.
delete_watch
Hosted only: deletes a watch.

What it does

GPU price comparison
Cheapest hourly rental rates per model across vendors.
Price change feed
What moved since yesterday.
Job cost estimate
Cost of a GPU job with sources and assumptions.
Stack optimizer
Cheapest cited plan per usage line or agent component.
Deals catalogue
Searchable feed with offer types and verification dates.
Price watches
Opt-in watch tools on the hosted endpoint.

Good for

  • Compare H100 rental prices
  • Estimate a 100-hour training cost
  • Spot price drops among providers
  • Find the cheapest hosting plan for an agent stack

Pricing

Free

Free, read-only, no API key

Prices change. Check thelanternworks.com before you buy.

Lantern Works GPU Prices: daily GPU rental price comparison FAQ

Do I need a key?

No API key or account.

How are prices sourced?

From each vendor's own pricing page, with source URL and check time.

How many tools does the local server have?

Nine, all read-only; the hosted endpoint has 13.

Are the deal links affiliate links?

Some are; they are flagged and, the site says, do not affect ranking.

Is Lantern Works GPU Prices: daily GPU rental price comparison free?

Yes. Lantern Works GPU Prices: daily GPU rental price comparison is free to use.

How do I add Lantern Works GPU Prices: daily GPU rental price comparison to Claude Code?

Run this command in your terminal: claude mcp add --transport http lantern-works-deals 'https://lantern-works-mcp.lantern-works.workers.dev/mcp?ref=mcp-registry'

What are the best alternatives to Lantern Works GPU Prices: daily GPU rental price comparison?

The closest alternatives to Lantern Works GPU Prices: daily GPU rental price comparison are rentgpu GPU rental price market data, Hundredth Run GPU Cloud Prices, GPUvec, Compute Screener and GPU Finder.

Where this comes from

  • Description: written from the project's README and the project's website.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers