Skip to main content
Glama

Reserve a GPU (automatic launch when back in stock)

gpucloud_reserve_server

Reserves a GPU machine that is out of stock: GPU Cloud launches the server AUTOMATICALLY as soon as it is back (machines are gone in 1 to 2 minutes), before other customers (first come, first served per machine). Requires a saved credit card (else httpStatus 402 PAYMENT_REQUIRED with the card link: an AI never enters card details), the user's explicit agreement (consent: true) and a maximum hourly price. The automatic reload is not required: the answer carries onFundsExhausted (the action at the threshold, chosen with the onFundsExhausted argument) and, when the reload is off, autoReloadWarning (show its message to the user). At launch, if the balance does not cover the first hour plus the hibernation threshold, only the missing amount is charged to the saved card; then the server is billed by the hour. Nothing is charged when reserving. [SPENDS MONEY] (permission: servers:reserve) [Requires a free GPU Cloud account and MCP key]

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "productId": "<productId>",
      "sshKeyId": "<sshKeyId>",
      "maxHourlyCad": "<maxHourlyCad>",
      "consent": "<consent>"
    },
    "name": "gpucloud_reserve_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoServer name (letters, digits, space, dot, dash, underscore).
consentYestrue ONLY once the user explicitly agreed to: "I authorize GPU Cloud to launch this server as soon as it is available, to charge my saved card the amount needed if my balance is not enough, then to bill it by the hour under the terms." (version 2026-10-10). Without it nothing is reserved.
sshKeyIdYesSSH key id installed on the server (gpucloud_list_ssh_keys).
productIdYesExact GPU machine to reserve (model and size, gpucloud_list_products), e.g. one shown out of stock.
templateIdNoOptional one-click template installed at launch (gpucloud_list_templates).
maxHourlyCadYesHighest hourly price (CAD) the user accepts: at least the current price (gpucloud_get_product), at most 5 times it. Above it at launch time, the reservation waits.
validityDaysNoDays the reservation stays valid (1 to 30, default 7); renewable in the console.
templateModelNoModel served by the vllm template.
onFundsExhaustedNoWhat happens to the launched server when the balance runs short: HIBERNATE (default: hibernated at its threshold with an hourly hibernation fee, restarted when the balance is back) or DELETE (no hibernation fee, kept running while the balance pays its next hour, then stopped). Spot machines are always DELETE. A server is never deleted while the account has credit left. When the balance covers only about 24 hours of what the account spends per hour, a first notice is sent while the servers still run, then two more about 24 hours and 1 hour before the deletion; a server is deleted with its data only once it is out of service (stopped or hibernated for lack of credit, or hibernated by the user for at least 72 hours), once the credit is exhausted (the balance no longer pays the next hour of the account's servers), after the three notices and at least 24 hours after the first. Adding credits cancels the deletion.
acceptAlternativeNotrue: an equivalent machine (same usage, at least the same GPU memory, never spot) may be launched when the exact one is not in stock. Default false: this exact machine only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / onFundsExhausted / description
      Previous value: -"What happens to the launched server when the balance reaches its threshold: HIBERNATE (default: kept 12 h with an hourly hibernation fee, restarted when the balance is back) or DELETE (deleted at once, data lost). Spot machines are always DELETE."New value: +"What happens to the launched server when the balance runs short: HIBERNATE (default: hibernated at its threshold with an hourly hibernation fee, restarted when the balance is back) or DELETE (no hibernation fee, kept running while the balance pays its next hour, then stopped). Spot machines are always DELETE. A server is never deleted while the account has credit left. When the balance covers only about 24 hours of what the account spends per hour, a first notice is sent while the servers still run, then two more about 24 hours and 1 hour before the deletion; a server is deleted with its data only once it is out of service (stopped or hibernated for lack of credit, or hibernated by the user for at least 72 hours), once the credit is exhausted (the balance no longer pays the next hour of the account's servers), after the three notices and at least 24 hours after the first. Adding credits cancels the deletion."
  2. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations: nothing is charged at reservation, the card is only charged the missing first-hour-plus-threshold amount at launch, then hourly billing, plus the 402 PAYMENT_REQUIRED path and the rule that the AI never enters card details. It also declares the required permission (servers:reserve) and that consent is mandatory — behavior an agent could not infer from readOnlyHint/destructiveHint alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action, its cost implication and the money flag are front-loaded, which is the right ordering for a spending tool. The long funds-exhaustion narrative duplicates the onFundsExhausted schema description and could be trimmed without losing anything.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter mutation with no output schema, the description covers cost timing, consent, card handling, the permission needed and even the response fields (onFundsExhausted, autoReloadWarning) the agent must act on. Nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all ten parameters including the onFundsExhausted enum and consent text. The description restates consent, max price and the funds-exhausted mechanics rather than adding syntax or edge-case meaning the schema lacks, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Reserves a GPU machine') plus the discriminating condition ('out of stock', automatic launch on restock). This is enough to tell it apart from an immediate-provision sibling like gpucloud_create_server without reading any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The when-to-use condition is explicit (machine is out of stock; first come, first served) and prerequisites are spelled out: saved card, explicit consent, maximum hourly price. It never names the alternative for in-stock machines (create_server / quote_server), so routing is inferred rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources