GrabGPU is an MCP server published by com.grabgpu, hosted at grabgpu.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 1 tool, including find_gpu.
Cloud GPU prices with live stock from 22 providers. Find where to rent an H100 or B300 now.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Find cloud GPUs to rent now: price per GPU hour and the stock each provider reported at the last hourly check. Rentable offers come first, cheapest first. Each offer has a rent_url that opens the provider (some are referral links, same price for the buyer).
| Parameter | Type | Description |
|---|---|---|
| gpu | string | GPU model, e.g. "H100", "B300", "RTX 4090". Omit for every model. |
| limit | integer | How many offers, default 20, at most 100. |
| billing | string | Only offers billed this way, ordered by that price. Left out: the entry price, whatever the billing. |
| in_stock | boolean | Default true: only offers the provider reports in stock. false: also offers that are out of stock or have unknown stock, for a full market view. |
| min_gpus |
None yet. Changes appear after a server's second daily check.
| integer |
| Smallest node size needed, e.g. 8 for an 8x node. |
| max_price | number | Highest USD per GPU hour. |
{
"name": "find_gpu",
"title": "Find a GPU to rent",
"description": "Find cloud GPUs to rent now: price per GPU hour and the stock each provider reported at the last hourly check. Rentable offers come first, cheapest first. Each offer has a rent_url that opens the provider (some are referral links, same price for the buyer).",
"inputSchema": {
"type": "object",
"properties": {
"gpu": {
"type": "string",
"description": "GPU model, e.g. \"H100\", \"B300\", \"RTX 4090\". Omit for every model."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "How many offers, default 20, at most 100."
},
"billing": {
"enum": [
"on_demand",
"spot",
"reserved"
],
"type": "string",
"description": "Only offers billed this way, ordered by that price. Left out: the entry price, whatever the billing."
},
"in_stock": {
"type": "boolean",
"description": "Default true: only offers the provider reports in stock. false: also offers that are out of stock or have unknown stock, for a full market view."
},
"min_gpus": {
"type": "integer",
"minimum": 1,
"description": "Smallest node size needed, e.g. 8 for an 8x node."
},
"max_price": {
"type": "number",
"description": "Highest USD per GPU hour.",
"exclusiveMinimum": 0
}
}
},
"outputSchema": {
"type": "object",
"required": [
"captured_at",
"unit",
"offers"
],
"properties": {
"unit": {
"type": "string"
},
"offers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"gpu": {
"type": "string",
"description": "GPU slug, e.g. \"nvidia-h100\""
},
"country": {
"type": [
"string",
"null"
]
},
"vram_gb": {
"type": [
"number",
"null"
]
},
"gpu_name": {
"type": "string"
},
"max_gpus": {
"type": [
"number",
"null"
],
"description": "Largest node the provider offers"
},
"provider": {
"type": "string",
"description": "Provider slug"
},
"rent_url": {
"type": "string",
"description": "Link to give the buyer; counts the click, then opens the provider"
},
"direct_url": {
"type": "string"
},
"is_referral": {
"type": "boolean",
"description": "rent_url ends in a referral link; the buyer pays the same price"
},
"availability": {
"enum": [
"in_stock",
"unknown",
"out_of_stock"
],
"type": "string",
"description": "Stock the provider reported for this GPU"
},
"provider_name": {
"type": "string"
},
"spot_max_gpus": {
"type": [
"number",
"null"
],
"description": "Largest node sold as spot; null when the provider lists none"
},
"gpu_count_range": {
"type": [
"string",
"null"
]
},
"usd_per_gpu_hour": {
"type": [
"number",
"null"
],
"description": "The entry rate: the on-demand price"
},
"reserved_max_gpus": {
"type": [
"number",
"null"
],
"description": "Largest node sold reserved; null when the provider lists none"
},
"spot_availability": {
"enum": [
"in_stock",
"unknown",
"out_of_stock"
],
"type": "string"
},
"on_demand_max_gpus": {
"type": [
"number",
"null"
],
"description": "Largest node sold on demand; null when the provider lists none"
},
"reserved_availability": {
"enum": [
"in_stock",
"unknown",
"out_of_stock"
],
"type": "string"
},
"spot_usd_per_gpu_hour": {
"type": [
"number",
"null"
]
},
"on_demand_availability": {
"enum": [
"in_stock",
"unknown",
"out_of_stock"
],
"type": "string"
},
"reserved_usd_per_gpu_hour": {
"type": [
"number",
"null"
]
},
"on_demand_usd_per_gpu_hour": {
"type": [
"number",
"null"
]
}
}
}
},
"captured_at": {
"type": "string",
"description": "When the prices and stock were collected"
}
}
},
"annotations": {
"title": "Find a GPU to rent",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use find_gpu to see which cloud GPUs can be rented now and where.
Names, descriptions and schemas were written by the server and are shown as data.