connormatthewdouglas/agent-work-stack-deals

Lantern Works tracks hourly GPU rental prices (H100, A100, RTX 4090 and more) across cloud providers, re-read every day from each vendor's own pricing page, with the quote, source link and check date for every rate, plus daily price history (since 2026-10-27). Agents get it through the comparegpuprices MCP tool (includehistory=true for price history) or plain JSON. "Cheapest" always means cheapest among tracked providers. It also keeps a directory of work-stack deals (scraping/unblock, email, search, hosting), ranked by customer value (price, free tier, fit), never by affiliate status. Some result links are referral links.
GPU prices: thelanternworks.com · /gpu/ · JSON api/v1/gpu-prices.json · history api/v1/gpu-prices/history.json · what moved since yesterday api/v1/gpu-price-changes.json (RSS)
Deals directory: thelanternworks.com/deals/ · About
Agent feed (JSON, no auth): thelanternworks.com/api/v1/deals.json (same bytes as /deals.json) · mirror: gist
Stack pricing: api/v1/stack-pricing.json
Query CLI: python3 querydeals.py --category unblock --max-price 20 (filter contract: USAGE.md)
Contact: lanternworks@agentmail.to
## MCP server (v0.3.44, read-only, stdio)
Free, read-only, no API key. Package lantern-works-deals-mcp on PyPI; MCP Registry name io.github.connormatthewdouglas/lantern-works-deals. Built on the official Python MCP SDK.
### Tools
Tool counts: 8 in the local package (stdio, below); 12 on the hosted endpoint (the same 8 plus createwatchkey, watchprice, listwatches, deletewatch).
| Tool | What it does |
| comparegpuprices | Hourly rental prices for a GPU model (e.g. H100, A100 SXM, RTX 4090) across tracked providers, cheapest first, each with sourceurl and checkedat. "Cheapest" means cheapest among tracked providers, not the whole market. includehistory=true adds each rate's price history and recent price changes (daily snapshots since 2026-10-27). Each rate has tierclass (on-demand, community, marketplace, interruptible, reserved, dedicated-monthly; also in the public JSON feed); ondemandonly=true keeps on-demand rates only. reserved = reservation/commitment "starting from" prices (e.g. Hyperstack reservations): they need a term contract, so they are left out of results and never called "cheapest" unless you pass includereserved=true (even then they sort after pay-as-you-go rates). Each result carries reportissueurl, a prefilled "wrong price" issue link. |
| getpricechanges | GPU price moves among tracked providers, newest first: old and new hourly price, changepct, direction and the vendor sourceurl. since (YYYY-MM-DD) returns every move on or after that date; without it, the latest day's moves. Optional gpu and kinds filters. Each change has a stable eventid (dedupe key) and rateid; pass cursor=nextcursor to page every change after it, oldest first, until hasmore is false. |
| optimizestack | Given monthly usage (pages scraped, proxy GB, emails, search queries, GPU hours/model), pick the cheapest tracked plan per line and total the monthly cost, with the calculation, sources and alternatives; unpublished prices are reported as unknown. |
| optimizeagentstack | Describe the agent in plain text (e.g. "scrapes 20k JS pages via 5 GB proxies, 3k searches, summarizes with an LLM, budget $300/mo"); a deterministic keyword parse (no LLM) maps it to components and returns the cheapest cited option per component with the math, sourceurl, verifiedat and a referral disclosure where applicable. Components with no cited price say "no sourced price tracked". |