Skip to main content
Glama
Sign In
GPU Manager MCP

GPU Manager MCP

by quxlzx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_gpu_processes

Retrieves processes using a specified GPU and reports per-process VRAM when NVML or rocm-smi exposes it; returns supported=false otherwise.

Instructions

Processes using the GPU with per-process VRAM, when the driver exposes it (NVML or rocm-smi). Returns supported=false otherwise.

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": {
      "gpu_id": "<gpu_id>"
    },
    "name": "get_gpu_processes"
  }
}

Input Schema

NameRequiredDescriptionDefault
gpu_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does add real value by disclosing a dependency on NVML or rocm-smi and a supported=false fallback, which an agent needs to handle. It does not clarify permissions, output shape beyond the notion of per-process VRAM, or what happens with an invalid gpu_id.

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

Conciseness5/5

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

Two short sentences, front-loaded with the core action, and every clause carries information: what is returned, the driver dependency, and the failure mode. No filler.

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

Completeness3/5

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

For a single-parameter read tool, the description covers the essential fallback behavior and result content, but there is no output schema and the sole required argument's format is unexplained. An agent could call it, but might pass the wrong identifier type.

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

Parameters2/5

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

There is one parameter (gpu_id) with 0% schema description coverage, so the description must compensate and does not. It never says whether gpu_id is an index, UUID, or PCI bus ID, nor where to obtain it, leaving the only required input ambiguous.

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

Purpose4/5

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

States a specific verb and resource: returns processes using the GPU with per-process VRAM. The word 'per-process' implicitly distinguishes it from aggregate siblings like get_gpu_memory and get_gpu_utilization, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

The description implies when the tool is useful (per-process attribution rather than aggregate GPU metrics) but never states when to prefer it over get_gpu_memory or get_all_gpu_metrics, and lists no preconditions such as needing a valid gpu_id from list_gpus.

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

Deploy Server

Other Tools