GPU Economy MCP Server for Claude
By GPU Economy
Overview
GPU Economy reads the public price pages and APIs of 60+ GPU clouds every hour — hyperscalers (AWS, Azure, Google Cloud, Oracle), neoclouds (Lambda, CoreWeave, Nebius, Crusoe, RunPod and others) and marketplaces (Vast.ai, Clore.ai) — and normalizes every listed rate to US dollars per GPU per hour. This server gives an AI agent those prices directly, instead of scraping pages. Tools (all read-only; no key, no account): Prices - list_gpus — every tracked GPU model (H100, H200, B200, B300, A100, L40S, RTX 4090/5090, MI300X and more) with VRAM, how many providers list it and the median on-demand rate. - gpu_prices — current rates for one GPU across providers, cheapest first; on-demand by default, or spot, community, serverless and reserved; optionally US or EU regions only. - provider_prices — every current rate at one provider. - provider_info — one provider: its type, regions, how its prices are read, and its cheapest on-demand rate on each GPU. Choosing and comparing - find_gpus — GPU models that meet a memory and price requirement (e.g. 80 GB+, under $3/hour), cheapest first. - compare_gpus — two GPU models side by side: VRAM, median and cheapest rate, price per GB, and every provider that lists both. - compare_providers — two providers on every GPU both list, and which is cheaper on each. Cost and planning - estimate_cost — what N GPUs cost for a number of hours at listed rates, at the cheapest providers and at the median, with the arithmetic. - commitment_savings — spot and 1- or 3-year committed rates against the same provider's on-demand rate, with the typical discount per term. - buy_vs_rent — a card's retail price against its rental rates: months of rental that equal the purchase. - token_cost — modelled cost per million output tokens from NVIDIA's published throughput; labelled as modelled, cards not comparable on it. Trends - price_index — the Cloud GPU Price Index: the median on-demand H100 SXM rate, weekly, hourly and monthly. - price_history — weekly
How to connect
- Claude: Open the GPU Economy listing in the Claude connectors directory and choose Connect. Claude listing GPU Economy exposes 16 tools here.
Tools
commitment_savings
Claudecompare_gpus
Claudecompare_providers
Claudeestimate_cost
Claudefetch
Claudefind_gpus
Claudegpu_prices
Claudelist_gpus
Claudeprice_history
Claudeprice_index
Claudeprovider_info
Claudeprovider_prices
Clauderecent_price_changes
Claudesearch
Claudetoken_cost
ClaudeLinks
Similar Apps
Listed on MCP App Store
Add this badge to your site or README. It links to this page.
HTML
<a href="https://mcp-app-store.keenethics-labs.com/app/gpu-economy"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>
Markdown
[](https://mcp-app-store.keenethics-labs.com/app/gpu-economy)






