GrabGPU
Server Details
Cloud GPU prices with live stock from 22 providers. Find where to rent an H100 or B300 now.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
Scored across 1 tool
With a single tool there is no possibility of misselection; find_gpu has one clear purpose (surface rentable GPU offers with price and stock).
The lone name follows a clean verb_noun snake_case pattern (find_gpu), which is exactly the convention an agent would expect for a search operation.
One tool is on the thin side for a marketplace surface; a search-only endpoint can be legitimate, but there is no way to refine results or fetch details of a specific offer.
The search-and-handoff flow is covered (rent_url offloads the transaction), but obvious gaps remain: no filtering by GPU model/memory/region, no get_offer detail lookup, and no way to compare or track a specific provider.
Available Tools
1 toolfind_gpuAInspect
Find cloud GPUs to rent now: price per GPU hour and the stock each provider reported at the last daily check. Rentable offers come first, cheapest first. Give the buyer rent_url; it opens the provider (some are referral links, same price for the buyer).
| Name | Required | Description | Default |
|---|---|---|---|
| gpu | No | GPU model, e.g. "H100", "B300", "RTX 4090". Omit for every model. | |
| limit | No | How many offers, default 20, at most 100. | |
| in_stock | No | Only offers the provider reports in stock. Default true. | |
| min_gpus | No | Smallest node size needed, e.g. 8 for an 8x node. | |
| max_price | No | Highest USD per GPU hour. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, and it does disclose real behavioral traits: data freshness is limited to the last daily provider check, results are ordered rentable-first then cheapest-first, and some rent_urls are referral links that do not change the buyer's price. It omits rate limits, error behavior, and pagination beyond the limit parameter.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the core action and return content, followed by ordering rules and the referral disclosure. No filler or repetition of the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description adequately characterizes the return data (price per GPU hour, reported stock, rent_url) and its ordering, which is what an agent needs to interpret results. Minor gaps remain around how stale/null pricing or out-of-stock entries appear in results.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so all five parameters (gpu, limit, in_stock, min_gpus, max_price) are already fully documented with examples and defaults. The description adds no parameter-level detail, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb and resource ("Find cloud GPUs to rent now") and immediately defines what the result contains: price per GPU hour and reported stock. It is unambiguous what the tool does, and no sibling tools exist to be confused with.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives clear context for use (finding GPUs available to rent now, with rentable offers surfaced first and sorted cheapest-first) and tells the agent what to do with the result ("Give the buyer rent_url"). There are no alternatives to exclude, so no when-not guidance is possible, but explicit selection criteria are absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- First observed
find_gpu
Related MCP Connectors
LLM and GPU rental prices: model price lookup, GPU listings, cheapest-GPU search, price history
Compare live GPU cloud rental prices and match workloads to the cheapest provider.
Live GPU spot market: 1,700+ offers, 10 provider feeds. History, watches, limit orders, no fee
Live VPS, bare metal and GPU hosting prices across ~75 providers, rescraped daily.
Related MCP Servers
- AlicenseAqualityCmaintenanceGlobal price benchmarking for AI inference across 2,600+ SKUs from 47 vendors. Query live pricing, market indexes, and model specs via 8 tools. Free tier available.849 npmMIT
- AlicenseBqualityCmaintenanceEnables users to describe their LLM fine-tuning job once and get the cheapest, fastest, and most balanced GPU options across a dozen cloud providers in seconds.7104MIT
- AlicenseAqualityAmaintenanceZero-quota GPU orchestration MCP server — lets AI agents discover, provision, and manage GPU compute across multi-datacenter partner nodes (H100/H200/B200) through a single control plane.126 npmMIT
- AlicenseNot gradedqualityDmaintenanceCompare AI inference pricing across 9 providers in real time. Routing recommendations, spend tracking, and budget alerts for AI agents.72 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.