Skip to main content
Glama
log-wade

datacenter-mcp-server

by log-wade
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

GPU Power & Cooling Optimizer

dc_gpu_cooling_optimizer
Read-onlyIdempotent

Calculate thermal loads and cooling needs for GPU/AI clusters. Recommends air or liquid cooling strategies and projects energy costs and savings.

Instructions

Optimize cooling infrastructure for GPU/AI workloads. Calculates thermal loads for modern GPU clusters (H100, A100, H200, B200, GB200), recommends cooling strategies (air, rear-door, direct liquid, immersion), and projects energy costs and savings.

Handles the unique thermal challenges of AI/ML deployments: extreme power density (30-120+ kW/rack), liquid cooling CDU sizing, coolant flow rates, and PUE impact analysis.

Args:

  • gpu_count (number): Total number of GPUs

  • gpu_model (string): "H100", "A100", "H200", "B200", or "GB200"

  • rack_count (number): Number of racks housing GPUs

  • cooling_type (string): "air", "direct_liquid", "rear_door", or "immersion"

  • ambient_temp_f (number): Ambient temperature in °F (default: 95)

  • pue_target (number): Target PUE ratio (default: 1.3)

Returns total heat load, per-rack density, cooling strategy recommendation, CDU sizing, coolant flow rates, chilled water plant capacity, annual energy costs, and liquid vs air savings analysis.

Examples:

  • "Cool 64 H100 GPUs across 8 racks with liquid cooling" -> gpu_count: 64, gpu_model: "H100", rack_count: 8, cooling_type: "direct_liquid"

  • "What cooling do I need for 16 GB200s?" -> gpu_count: 16, gpu_model: "GB200", rack_count: 2, cooling_type: "immersion"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gpu_countYesTotal number of GPU accelerators in the deployment
gpu_modelYesGPU model for TDP lookup: H100 (700W), A100 (400W), H200 (700W), B200 (1000W), GB200 (1200W)
pue_targetYesTarget Power Usage Effectiveness for facility evaluation
rack_countYesNumber of racks in the GPU deployment
cooling_typeYesCooling strategy: air (traditional), rear_door (15-30 kW/rack), direct_liquid (30-60 kW/rack), immersion (>60 kW/rack)
ambient_temp_fYesAmbient supply air temperature in Fahrenheit (typical: 72-75°F)
electricity_cost_per_kwhNoAverage electricity cost in $/kWh (default: $0.08)

Tool Definition Quality

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description is consistent with these, and adds valuable context about what the tool computes (CDU sizing, coolant flow, PUE impact). It does not state assumptions or limitations, but annotation coverage lowers the burden.

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 description is front-loaded with purpose, followed by capability context, a structured Args list, return summary, and examples. It is longer than necessary due to repeating schema details, but the structure is logical and the examples aid usability.

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?

The tool is complex (7 params, no output schema), and the description lists return values and gives examples. However, it omits the electricity_cost_per_kwh parameter and lists defaults for two parameters that are required per schema, which could mislead an agent into omitting them. This gap prevents full completeness.

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 covers 100% of parameters with descriptions, so baseline is 3. The description's Args section largely repeats schema info but adds defaults for ambient_temp_f and pue_target (not in schema) and omits electricity_cost_per_kwh. This provides some extra meaning but also introduces inconsistency.

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?

The description uses a specific verb ('Optimize cooling infrastructure') and concretely enumerates outputs: thermal loads, cooling strategy, energy costs/savings. It clearly differentiates from siblings like dc_calculate_cooling_load by focusing on GPU/AI workloads and including cost projection.

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 description clearly scopes the tool to GPU/AI workloads, listing supported GPU models and cooling types, which implies when to use it. However, it does not explicitly compare against sibling tools or mention exclusions, so it lacks explicit when-not-to-use guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/log-wade/datacenter-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server