Find and price cloud GPUs, estimate job costs, and manage your CoreHu machines with your consent.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Estimate the USD cost of running a GPU model for a number of hours on CoreHu, from the cheapest free machine right now. Estimate only; nothing is reserved.
How many hours the job runs
Exact GPU model name, e.g. "RTX 4090"
Number of GPUs in one machine (1–16)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http gpu-cloud https://corehu.com/api/mcp/account
Tool list last changed Nov 12, 2026.
Estimate the USD cost of running a GPU model for a number of hours on CoreHu, from the cheapest free machine right now. Estimate only; nothing is reserved.
| Argument | Type | Description |
|---|---|---|
| hours* | number | How many hours the job runs |
| gpuCount | integer | Number of GPUs in one machine (1–16) |
| gpuModel* | string | Exact GPU model name, e.g. "RTX 4090" |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"gpuModel",
"hours"
],
"properties": {
"hours": {
"type": "number",
"maximum": 10000,
"description": "How many hours the job runs",
"exclusiveMinimum": 0
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1,
"description": "Number of GPUs in one machine (1–16)"
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"minLength": 1,
"description": "Exact GPU model name, e.g. \"RTX 4090\""
}
}
}Starting hourly USD price for every GPU model in the CoreHu catalog (or models matching a name).
| Argument | Type | Description |
|---|---|---|
| gpuModel | string | Part of the GPU model name to filter by, e.g. "4090"; omit for all models |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"gpuModel": {
"type": "string",
"maxLength": 40,
"description": "Part of the GPU model name to filter by, e.g. \"4090\"; omit for all models"
}
}
}Search free CoreHu GPU machines in the live catalog. Returns up to 20 offers sorted by hourly USD price, with a link to rent each one.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum number of offers to return (default 20) |
| country | string | ISO 3166-1 alpha-2 country code |
| gpuCount | integer | Number of GPUs in one machine (1–16) |
| gpuModel | string | Part of the GPU model name, e.g. "RTX 4090" or "H100" |
| minVramGb | number | Minimum VRAM per GPU in GB |
| maxUsdPerHour | number | Maximum hourly price in USD for the whole machine |
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Maximum number of offers to return (default 20)"
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "ISO 3166-1 alpha-2 country code"
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1,
"description": "Number of GPUs in one machine (1–16)"
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"description": "Part of the GPU model name, e.g. \"RTX 4090\" or \"H100\""
},
"minVramGb": {
"type": "number",
"maximum": 512,
"minimum": 1,
"description": "Minimum VRAM per GPU in GB"
},
"maxUsdPerHour": {
"type": "number",
"maximum": 1000,
"description": "Maximum hourly price in USD for the whole machine",
"exclusiveMinimum": 0
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 12, 2026.
What changed in this server's tools since we started watching, newest first. Each change is scanned again.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"gpuModel",
"hours"
],
"properties": {
"hours": {
"type": "number",
"maximum": 10000,
"exclusiveMinimum": 0
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"minLength": 1,
"description": "Exact GPU model name, e.g. \"RTX 4090\""
}
}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"gpuModel",
"hours"
],
"properties": {
"hours": {
"type": "number",
"maximum": 10000,
"description": "How many hours the job runs",
"exclusiveMinimum": 0
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1,
"description": "Number of GPUs in one machine (1–16)"
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"minLength": 1,
"description": "Exact GPU model name, e.g. \"RTX 4090\""
}
}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"gpuModel": {
"type": "string",
"maxLength": 40
}
}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"gpuModel": {
"type": "string",
"maxLength": 40,
"description": "Part of the GPU model name to filter by, e.g. \"4090\"; omit for all models"
}
}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "ISO 3166-1 alpha-2 country code"
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"description": "Part of the GPU model name, e.g. \"RTX 4090\" or \"H100\""
},
"minVramGb": {
"type": "number",
"maximum": 512,
"minimum": 1,
"description": "Minimum VRAM per GPU in GB"
},
"maxUsdPerHour": {
"type": "number",
"maximum": 1000,
"exclusiveMinimum": 0
}
}
}{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Maximum number of offers to return (default 20)"
},
"country": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "ISO 3166-1 alpha-2 country code"
},
"gpuCount": {
"type": "integer",
"maximum": 16,
"minimum": 1,
"description": "Number of GPUs in one machine (1–16)"
},
"gpuModel": {
"type": "string",
"maxLength": 40,
"description": "Part of the GPU model name, e.g. \"RTX 4090\" or \"H100\""
},
"minVramGb": {
"type": "number",
"maximum": 512,
"minimum": 1,
"description": "Minimum VRAM per GPU in GB"
},
"maxUsdPerHour": {
"type": "number",
"maximum": 1000,
"description": "Maximum hourly price in USD for the whole machine",
"exclusiveMinimum": 0
}
}
}