An agent can connect on its own if it already holds GPUFINDER_TOKEN.Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.
tools.schemasevery tool has an object input schema
pass
tools.annotations8 of 8 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 1,976 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump
stability25 · weight 15
warn
stability.changes8 tool changes in 30 days
fail
stability.rug_pull7 tools kept their name but changed most of their description in 30 days; review before trusting them
dependenciesn/a · weight 15
n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package
8 tools, about 1,976 tokens to load them all · tool set 01199f3cfd61 · tools last changed 2026-10-17 · checked 2026-10-20 12:45 UTC
Tool changes
get_usagechangeddescriptionmeaning changed
before
Read this account's shared REST/MCP usage, effective allowance, remaining units and UTC resets. Works after monthly exhaustion; spends no monthly units and remains rate controlled.
after · 33% of words in common
Show this API key's usage across REST and MCP: plan allowance, units used and remaining, and UTC reset times. Use it before large paginated reads or after a quota_exceeded error. Spends no monthly units and works after the monthly allowance is exhausted, but is still rate limited.
Compare cheapest listed and cheapest currently observed in-stock offers for a GPU and count. Includes whole node and per GPU hourly USD prices, timestamps and unknown availability. The whole snapshot costs one data unit; collected stock is not a capacity guarantee.
after · 42% of words in common
Answer "what is the cheapest way to rent this GPU now": the cheapest listed offer and the cheapest offer observed in stock for one GPU model and node size, each with provider, region, whole node and per GPU hourly USD price, availability status and check time, plus how many providers were compared. Use it for a single recommendation; use get_prices for every offer. The whole snapshot costs one data unit; collected stock is not a capacity guarantee.
get_data_statuschangeddescriptionmeaning changed
before
Read collection timestamps and provider freshness. This is a metered data operation, not an anonymous health check.
after · 23% of words in common
Report how fresh GPU Finder's data is: when price and availability collection last completed, and each provider's last success, last run, consecutive failures and last error. Use it to decide whether a price or availability answer may be stale. Costs one data unit; it is not an anonymous health check.
get_price_historychangeddescription, input schema
before
Read monthly GPU price history, at most 12 UTC months per provider series. Pages default to 20 rows, maximum 100; each page costs one data unit. Reuse the same filters and page limit with nextCursor.
after · 50% of words in common
Show how one GPU model's price changed month by month per provider: on-demand and spot USD per whole node hour for up to 12 UTC months. Use it for trends; use get_prices for current prices. Pages default to 20 rows, maximum 100; each page costs one data unit. Reuse the same filters and page limit with nextCursor.
Read observed seven-day availability coverage for a GPU, optionally one provider. Missing coverage remains unknown. Pages default to 20 rows, maximum 100.
after · 27% of words in common
Show day-by-day stock for one GPU model over the last seven days, per provider and node size: instances observed available versus total each day. Optionally limit to one provider. Use it to judge how reliably a GPU can be found in stock; prices come from get_prices. Days without observations are unknown, not zero. Pages default to 20 rows, maximum 100; each page costs one data unit.
Compare listed prices in USD per whole node hour for a GPU and count. Prices and availability reflect collected data, not a live capacity guarantee. Pages default to 20 rows, maximum 100.
after · 41% of words in common
List every provider offer for one GPU model and node size: provider, instance type, region, GPU count, on-demand and spot USD price per whole node hour, links and last update. Use it for the full price table; use get_market_snapshot for only the cheapest offer, get_availability for stock and get_price_history for trends. Prices reflect collected data, not a live capacity guarantee. Pages default to 20 rows, maximum 100; each page costs one data unit.
List GPU cloud providers, price ranges and GPU Finder links. Pages default to 20 rows, maximum 100; each page costs one data unit.
after · 39% of words in common
List GPU cloud providers: name and slug, GPU and instance counts, min/max hourly USD price, egress cost per GB and free egress allowance, website and GPU Finder links, and last update time. Use it to find valid provider slugs or compare providers overall; use get_prices for one GPU's offers. Pages default to 20 rows, maximum 100; each page costs one data unit.
List GPU catalog models and price ranges. Pages default to 20 rows, maximum 100; each page costs one data unit.
after · 34% of words in common
List the GPU models GPU Finder tracks: canonical name and slug, VRAM, memory type, bandwidth, interconnect, provider and instance counts, and min/max hourly USD price. Use it to find valid gpu names for the other tools or to compare GPU specs; use get_prices for per-provider offers. Pages default to 20 rows, maximum 100; each page costs one data unit.
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
Endpoints
remote
auth
reachable
uptime 30d
p50
protocol
last ok
https://gpufinder.dev/mcpstreamable-http
api_key ${GPUFINDER_TOKEN}
yes
100%
433 ms
2026-07-28
2026-10-20
Tools (8)
get_availabilityread-only
Show day-by-day stock for one GPU model over the last seven days, per provider and node size: instances observed available versus total each day. Optionally limit to one provider. Use it to judge how reliably a GPU can be found in stock; prices come from get_prices. Days without observations are unknown, not zero. Pages default to 20 rows, maximum 100; each page costs one data unit.
get_data_statusread-only
Report how fresh GPU Finder's data is: when price and availability collection last completed, and each provider's last success, last run, consecutive failures and last error. Use it to decide whether a price or availability answer may be stale. Costs one data unit; it is not an anonymous health check.
get_market_snapshotread-only
Answer "what is the cheapest way to rent this GPU now": the cheapest listed offer and the cheapest offer observed in stock for one GPU model and node size, each with provider, region, whole node and per GPU hourly USD price, availability status and check time, plus how many providers were compared. Use it for a single recommendation; use get_prices for every offer. The whole snapshot costs one data unit; collected stock is not a capacity guarantee.
get_price_historyread-only
Show how one GPU model's price changed month by month per provider: on-demand and spot USD per whole node hour for up to 12 UTC months. Use it for trends; use get_prices for current prices. Pages default to 20 rows, maximum 100; each page costs one data unit. Reuse the same filters and page limit with nextCursor.
get_pricesread-only
List every provider offer for one GPU model and node size: provider, instance type, region, GPU count, on-demand and spot USD price per whole node hour, links and last update. Use it for the full price table; use get_market_snapshot for only the cheapest offer, get_availability for stock and get_price_history for trends. Prices reflect collected data, not a live capacity guarantee. Pages default to 20 rows, maximum 100; each page costs one data unit.
get_usageread-only
Show this API key's usage across REST and MCP: plan allowance, units used and remaining, and UTC reset times. Use it before large paginated reads or after a quota_exceeded error. Spends no monthly units and works after the monthly allowance is exhausted, but is still rate limited.
list_gpusread-only
List the GPU models GPU Finder tracks: canonical name and slug, VRAM, memory type, bandwidth, interconnect, provider and instance counts, and min/max hourly USD price. Use it to find valid gpu names for the other tools or to compare GPU specs; use get_prices for per-provider offers. Pages default to 20 rows, maximum 100; each page costs one data unit.
list_providersread-only
List GPU cloud providers: name and slug, GPU and instance counts, min/max hourly USD price, egress cost per GB and free egress allowance, website and GPU Finder links, and last update time. Use it to find valid provider slugs or compare providers overall; use get_prices for one GPU's offers. Pages default to 20 rows, maximum 100; each page costs one data unit.
protogrid