Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@datacenter-mcp-server Calculate cooling load for 500kW IT load in Miami with N+1 redundancy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Mission-critical data center engineering tools for AI agents. 8 professional-grade calculation engines covering cooling, power, GPU thermal optimization, UPS/battery sizing, tier classification, and commissioning workflows.
Built on the Model Context Protocol (MCP) standard — works with Claude Desktop, Cursor, Windsurf, Cline, and any MCP-compatible client.
Add to your claude_desktop_config.json:
{
"mcpServers": {
"datacenter": {
"command": "npx",
"args": ["-y", "datacenter-mcp-server"]
}
}
}Add to your MCP settings:
{
"datacenter": {
"command": "npx",
"args": ["-y", "datacenter-mcp-server"]
}
}TRANSPORT=http PORT=3001 API_KEY=your-secret npx datacenter-mcp-serverRelated MCP server: thermal-mcp-server
Calculate ASHRAE-compliant cooling requirements for any data center facility. Inputs include IT load, redundancy level, climate zone, altitude, and humidity targets. Returns tonnage, airflow, chilled water capacity, and energy estimates.
Analyze electrical distribution from utility feed through UPS, PDU, and rack-level power. Supports N, N+1, 2N, and 2N+1 redundancy configurations with efficiency and cost analysis.
Evaluate facility design against Uptime Institute Tier I-IV standards. Identifies compliance gaps and provides actionable upgrade recommendations.
Generate L1-L5 commissioning workflows with phase sequencing, test procedures, and documentation requirements per ASHRAE Guideline 0.
Analyze rack power density configurations from 5 kW to 100+ kW per rack. Covers cooling strategy selection, weight loading, and power distribution.
Optimize cooling infrastructure for GPU/AI workloads (H100, A100, H200, B200, GB200). Calculates thermal loads, recommends cooling strategies (air, rear-door, direct liquid, immersion), sizes CDUs, and projects energy savings.
Size UPS modules and battery systems with N/N+1/2N/2N+1 redundancy. Compares VRLA vs lithium-ion with 10-year TCO analysis, floor space estimates, and weight calculations.
Query ASHRAE standards, Uptime Institute tier requirements, and industry best practices for data center design and operations.
All calculations comply with:
ASHRAE TC 9.9 thermal guidelines
Uptime Institute Tier Standard topology
NFPA 70 / NEC electrical code
ASHRAE Guideline 0 commissioning
# Install dependencies
npm install
# Build
npm run build
# Run tests (264 tests across 7 suites)
npm test
# Start in stdio mode (MCP default)
npm start
# Start in HTTP mode
npm run start:http
# Inspect with MCP Inspector
npm run inspectsrc/
index.ts # MCP server entry point, tool registration
types.ts # TypeScript interfaces for all tools
constants.ts # Engineering constants and reference data
middleware.ts # Express middleware (auth, rate limiting, CORS)
schemas/ # Zod validation schemas per tool
services/ # Calculation engines per tool
tests/ # Jest test suites (264 tests)MIT - NextGen Mission Critical
Analyze power redundancy configuration for a mission-critical data center.
Calculates UPS module count and sizing, generator count and total capacity, PDU requirements and switchgear feeds, electrical efficiency chain losses, UPS loading percentage, and concurrent maintainability / fault tolerance assessment.
Supports N, N+1, 2N, and 2N+1 redundancy configurations.
Args:
it_load_kw (number): Total IT load in kW
redundancy_config (string): "N", "N+1", "2N", or "2N+1"
ups_module_size_kw (number): Individual UPS module capacity (default: 500 kW)
generator_size_kw (number): Individual generator capacity (default: 2000 kW)
ups_efficiency (number): UPS efficiency 0.8-0.99 (default: 0.95)
pdu_efficiency (number): PDU efficiency 0.9-0.999 (default: 0.98)
transformer_efficiency (number): Transformer efficiency (default: 0.985)
Returns structured JSON with complete power infrastructure sizing and recommendations.
Examples:
"Size a 2N UPS system for 3 MW" -> it_load_kw: 3000, redundancy_config: "2N"
"What do I need for N+1 at 1.5 MW with 750 kW UPS modules?" -> it_load_kw: 1500, redundancy_config: "N+1", ups_module_size_kw: 750
| Name | Required | Description | Default |
|---|---|---|---|
| it_load_kw | Yes | Total IT electrical load in kilowatts (kW) | |
| pdu_efficiency | No | Power distribution unit efficiency (default: 0.98 = 98%) | |
| ups_efficiency | No | UPS efficiency at operating load (default: 0.95 = 95%) | |
| generator_size_kw | No | Individual generator capacity in kW (default: 2000 kW / 2500 kVA) | |
| redundancy_config | Yes | Power redundancy configuration: N (none), N+1 (one spare), 2N (fully redundant), 2N+1 (redundant + spare) | |
| ups_module_size_kw | No | Individual UPS module capacity in kW (default: 500 kW) | |
| transformer_efficiency | No | Transformer efficiency (default: 0.985 = 98.5%) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as read-only, idempotent, and non-destructive, so the bar is lower. The description adds value by listing the calculations performed and stating it returns structured JSON, but it does not disclose deeper behavioral details such as error handling, prerequisites, or response format specifics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear opening purpose, a list of calculations, an Args section, and Examples. Every sentence contributes meaningful information, and the length is appropriate for a tool with seven parameters; there is no fluff or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema, and while the description lists many outputs and says it returns structured JSON, it does not specify the JSON keys or structure. For a complex tool without an output schema, more detail about the return format would be needed for full completeness, but the description still gives a solid high-level overview.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers 100% of parameters with descriptions and defaults, so the baseline is 3. The description adds value through its Args list (though largely duplicative) and especially the two concrete examples, which illustrate how to map natural language queries to actual parameter values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool analyzes power redundancy configuration for data centers and lists specific calculations (UPS module count, generator capacity, PDU requirements, etc.). This verb+resource combination distinguishes it from sibling tools like cooling load or tier classification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by focusing on power redundancy analysis and provides two examples demonstrating common scenarios. However, it does not explicitly state when to use this tool versus alternatives or mention exclusions, so the guidance is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Analyze rack density classification and recommend appropriate cooling strategies.
Classifies rack density (low/medium/high/ultra-high/liquid-cooled), recommends cooling approach, estimates airflow requirements per rack, and flags containment and liquid cooling thresholds.
Args:
rack_count (number): Total number of racks
avg_kw_per_rack (number): Average power per rack in kW
floor_area_sqft (number): Optional white space area for W/sqft calculation
cooling_type (string): Optional current/planned cooling type
Returns density classification, recommended cooling strategy, airflow estimates, and recommendations.
Examples:
"I have 200 racks at 8 kW each in 10,000 sqft" -> rack_count: 200, avg_kw_per_rack: 8, floor_area_sqft: 10000
"Cooling strategy for 50 GPU racks at 40 kW" -> rack_count: 50, avg_kw_per_rack: 40
| Name | Required | Description | Default |
|---|---|---|---|
| rack_count | Yes | Total number of IT racks / cabinets | |
| cooling_type | No | Current or planned cooling type (e.g., 'air-cooled DX', 'chilled water', 'rear-door heat exchanger') | |
| avg_kw_per_rack | Yes | Average power draw per rack in kW (e.g., 8 for typical enterprise, 40+ for GPU/HPC) | |
| floor_area_sqft | No | Total white space floor area in square feet (for W/sqft calculation) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate those. It adds value by detailing what the tool returns: density classification, cooling strategy, airflow estimates, and thresholds for containment and liquid cooling. This gives the agent a clear picture of the tool's behavior and output beyond the annotation hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a concise intro, a clear Args list, a Returns line, and illustrative examples. Every sentence serves a purpose, and the overall length is appropriate for the tool's complexity. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description fully covers what the tool does, the parameters it accepts, and the outputs it produces. With no output schema, the description carries the burden of explaining return values, and it does so clearly (classification, strategy, airflow, recommendations). Examples add practical context, making it complete for an analysis tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% parameter coverage with detailed descriptions, so the baseline is 3. The description goes beyond the schema by providing concrete value examples (e.g., 8 kW typical enterprise, 40+ GPU) and natural-language mapping examples, which adds practical meaning for parameter selection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description starts with a specific verb ('Analyze') and resource ('rack density') and clearly states the tool's purpose: to classify density and recommend cooling strategies. This distinguishes it from siblings like dc_calculate_cooling_load or dc_gpu_cooling_optimizer, which focus on different aspects of cooling.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use the tool through examples and a returns summary, but it doesn't explicitly state when not to use it or point to sibling alternatives. This is a strong but not explicit usage guide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Assess a data center's Uptime Institute Tier classification based on its infrastructure configuration.
Evaluates power redundancy, cooling redundancy, distribution paths, concurrent maintainability, and fault tolerance against Tier I-IV requirements. Identifies gaps between current infrastructure and target tier.
Args:
target_tier (number): Target Tier level 1-4
power_redundancy (string): Current power config ("N", "N+1", "2N", "2N+1")
cooling_redundancy (string): Current cooling config
distribution_paths (number): Number of independent power paths
concurrently_maintainable (boolean): Can maintain without IT impact?
fault_tolerant (boolean): Automatic fault handling?
generator_backed (boolean): Generator backup available?
ups_runtime_minutes (number): UPS battery runtime (default: 10)
fire_suppression (boolean): Clean agent suppression installed?
monitoring_system (boolean): BMS/DCIM installed?
Returns target vs achieved tier, gap analysis with severity ratings, uptime expectations, and recommendations.
Examples:
"Does my N+1 facility qualify for Tier III?" -> target_tier: 3, power_redundancy: "N+1", cooling_redundancy: "N+1", distribution_paths: 1, concurrently_maintainable: false, fault_tolerant: false, generator_backed: true
"Assess our 2N facility against Tier IV" -> target_tier: 4, power_redundancy: "2N", cooling_redundancy: "2N", distribution_paths: 2, concurrently_maintainable: true, fault_tolerant: true, generator_backed: true
| Name | Required | Description | Default |
|---|---|---|---|
| target_tier | Yes | Target Uptime Institute Tier level (1-4) | |
| fault_tolerant | Yes | Whether any single component failure is automatically handled without IT impact | |
| fire_suppression | No | Whether clean agent fire suppression is installed in the IT space | |
| generator_backed | Yes | Whether the facility has generator backup power | |
| power_redundancy | Yes | Current power redundancy configuration | |
| monitoring_system | No | Whether BMS/DCIM monitoring system is installed | |
| cooling_redundancy | Yes | Current cooling redundancy configuration | |
| distribution_paths | Yes | Number of independent power distribution paths to IT equipment | |
| ups_runtime_minutes | No | UPS battery runtime in minutes at full load (default: 10 min) | |
| concurrently_maintainable | Yes | Whether any capacity component can be maintained without impacting IT load |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior, so the bar is lower. The description adds useful context: it evaluates specific infrastructure aspects, identifies gaps, and returns target vs achieved tier, gap analysis with severity ratings, uptime expectations, and recommendations. This goes beyond the annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear overview, evaluation criteria, return value summary, parameter list, and examples. It is appropriately sized for a 10-parameter tool; every sentence adds value and the most important information (purpose) is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (10 params, no output schema), the description provides a complete picture: it states what the tool does, what it evaluates, what it returns, and includes two concrete examples. The annotations and full schema coverage cover safety and parameter details, so no critical context is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description's Args list repeats parameter names and brief meanings, but the examples provide additional semantic value by showing how parameters like power_redundancy, cooling_redundancy, and distribution_paths are combined for realistic scenarios (e.g., 2N facility for Tier IV), which enhances understanding beyond the schema's dry definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool assesses a data center's Uptime Institute Tier classification based on infrastructure configuration, a specific verb+resource+scope. It distinguishes from sibling tools like dc_analyze_power_redundancy by covering multiple dimensions (power, cooling, distribution, maintainability, fault tolerance) rather than a single aspect.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains what inputs are evaluated and mentions identifying gaps between current infrastructure and target tier, implying when to use it (when a tier classification assessment is needed). Examples show common queries like 'Does my N+1 facility qualify for Tier III?', but it does not explicitly discuss alternatives or exclusions relative to sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Calculate the total cooling load for a data center facility based on IT load, PUE, and environmental factors.
This tool computes cooling capacity requirements in kW, tons, and BTU/hr, estimates required airflow in CFM, rates the facility's PUE efficiency, and provides actionable recommendations for cooling system design.
Accounts for: IT heat rejection, electrical overhead losses, lighting loads, humidification, and altitude derating above 5,000 ft.
Args:
it_load_kw (number): Total IT electrical load in kW
pue (number): Power Usage Effectiveness ratio (1.0-3.0)
safety_factor (number): Design margin (default 1.15 = 15%)
lighting_area_sqft (number): Floor area for lighting heat gain
include_humidification (boolean): Include humidification load
altitude_ft (number): Site altitude for equipment derating
design_outdoor_temp_f (number): ASHRAE design day temperature
Returns structured JSON with cooling_load_kw, cooling_load_tons, cooling_load_btu, estimated_airflow_cfm, pue_rating, and engineering recommendations.
Examples:
"Calculate cooling for a 2 MW data center with PUE of 1.4" -> it_load_kw: 2000, pue: 1.4
"What cooling do I need for 500 kW at 6000 ft altitude?" -> it_load_kw: 500, pue: 1.5, altitude_ft: 6000
| Name | Required | Description | Default |
|---|---|---|---|
| pue | Yes | Power Usage Effectiveness — ratio of total facility power to IT power (typically 1.2-1.8) | |
| it_load_kw | Yes | Total IT electrical load in kilowatts (kW) | |
| altitude_ft | No | Site altitude in feet above sea level (equipment derating applied above 5,000 ft) | |
| safety_factor | No | Design safety factor applied to cooling capacity (default: 1.15 = 15% margin) | |
| lighting_area_sqft | No | White space floor area in square feet (for lighting/misc heat gain calculation) | |
| design_outdoor_temp_f | No | Design outdoor dry-bulb temperature in Fahrenheit (ASHRAE 0.4% cooling design day) | |
| include_humidification | No | Whether to include humidification load in calculation (adds ~7%) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, and non-destructive. The description adds context about included calculations (IT heat rejection, electrical losses, lighting, humidification, altitude derating) and return format, exceeding the annotation baseline. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured: purpose, capabilities, factors, args, returns, examples. It is front-loaded with key info. However, the Args section duplicates the schema, adding redundancy and length without new value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex tool with no output schema, the description covers return fields and calculation factors, plus examples. It lacks emphasis on required parameters and edge cases, but is otherwise complete for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The Args section mostly reiterates schema descriptions. The examples add some semantic mapping from natural language to parameters, but not enough to elevate beyond baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool calculates total cooling load for a data center, with specific outputs (kW, tons, BTU/hr, CFM, PUE rating, recommendations). It differentiates from siblings by focusing on cooling load, while others address power redundancy, tier classification, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context on what the tool does and its inputs (factors like IT load, PUE, environmental factors), with examples of typical use. However, it does not explicitly mention alternatives or when not to use this tool, though sibling tools are distinct.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a comprehensive data center commissioning plan following ASHRAE guidelines (Levels 1-5).
Creates a structured commissioning plan with test procedures, durations, milestones, and prerequisites scaled to facility size and tier complexity.
Commissioning Levels:
L1: Factory Witness Testing
L2: Component Verification & Startup
L3: System Functional Performance Testing
L4: Integrated Systems Testing (load bank, concurrent maintenance, fault injection)
L5: Operational Sustainability (seasonal verification)
Args:
facility_size_kw (number): Design IT capacity in kW
tier_level (number): Target Tier 1-4 (affects test complexity)
include_levels (number[]): Which commissioning levels to include [1,2,3,4,5]
custom_systems (string[]): Optional custom systems list
Returns structured plan with phases, test procedures, durations, milestones, and recommendations.
Examples:
"Generate a full Cx plan for a 5 MW Tier III facility" -> facility_size_kw: 5000, tier_level: 3, include_levels: [1,2,3,4,5]
"Just L3 and L4 for a 1 MW Tier II" -> facility_size_kw: 1000, tier_level: 2, include_levels: [3,4]
| Name | Required | Description | Default |
|---|---|---|---|
| tier_level | Yes | Target Uptime Institute Tier level (affects test complexity and duration) | |
| custom_systems | No | Optional list of specific systems to commission (defaults to standard MEP systems) | |
| include_levels | Yes | Commissioning levels to include: 1=Factory Witness, 2=Component Verification, 3=System Verification, 4=Integrated Systems, 5=Operational Sustainability | |
| facility_size_kw | Yes | Total IT design capacity of the facility in kW |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnly/idempotent annotations, the description discloses meaningful behavioral details: it follows ASHRAE levels, scales to facility size and tier complexity, and returns a structured plan with phases, test procedures, durations, milestones, and recommendations. It also explains the meaning of each commissioning level, providing transparency about what the generated plan contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and front-loaded with the core purpose. It includes the level definitions, an Args section, and examples. The Args section partially duplicates the schema descriptions, but the overall organization is logical and each section serves a clear role. It is longer than minimal but appropriate for a complex generation tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, the description appropriately explains the return value ('structured plan with phases, test procedures, durations, milestones, and recommendations'). It also defines the commissioning levels, parameter semantics, and provides examples. This is a complete, self-contained description for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already covers 100% of the parameters with descriptions, so the baseline is 3. The description adds value through the commissioning-level definitions and two realistic examples that show how to interpret user phrasing into exact parameter values (e.g., '5 MW Tier III' -> facility_size_kw: 5000, tier_level: 3). This practical mapping goes beyond the schema's static field descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb and resource: 'Generate a comprehensive data center commissioning plan following ASHRAE guidelines (Levels 1-5).' This clearly distinguishes it from sibling tools like dc_calculate_cooling_load or dc_assess_tier_classification. It also outlines the structured output and scaling behavior, making the tool's purpose unmistakable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context by explaining what the plan includes and how it scales, and it supplies concrete examples mapping natural-language requests to parameter values. It does not explicitly state when not to use this tool or name alternatives, but none of the sibling tools overlap with commissioning-plan generation, so the usage context is sufficiently clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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"
| Name | Required | Description | Default |
|---|---|---|---|
| gpu_count | Yes | Total number of GPU accelerators in the deployment | |
| gpu_model | Yes | GPU model for TDP lookup: H100 (700W), A100 (400W), H200 (700W), B200 (1000W), GB200 (1200W) | |
| pue_target | Yes | Target Power Usage Effectiveness for facility evaluation | |
| rack_count | Yes | Number of racks in the GPU deployment | |
| cooling_type | Yes | Cooling strategy: air (traditional), rear_door (15-30 kW/rack), direct_liquid (30-60 kW/rack), immersion (>60 kW/rack) | |
| ambient_temp_f | Yes | Ambient supply air temperature in Fahrenheit (typical: 72-75°F) | |
| electricity_cost_per_kwh | No | Average electricity cost in $/kWh (default: $0.08) |
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.
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.
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.
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.
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.
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.
Look up data center engineering reference data including Tier requirements, PUE benchmarks, rack density classifications, and commissioning phases.
Args:
category (string): One of "tier_requirements", "pue_benchmarks", "rack_density", "commissioning_phases"
tier (number): Optional — filter tier requirements by specific tier (1-4)
Returns reference data tables for data center engineering decisions.
Examples:
"What are the Tier III requirements?" -> category: "tier_requirements", tier: 3
"Show me PUE benchmarks" -> category: "pue_benchmarks"
"Rack density classifications" -> category: "rack_density"
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Optional: specific tier level to filter (1-4) | |
| category | Yes | Reference data category to look up |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds 'Returns reference data tables' and clarifies the tier filter, providing some context beyond annotations. No additional behavioral details like rate limits or error handling are included, but none are critical for this read-only tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with purpose, Args, Returns, and Examples sections. The Args section somewhat repeats the schema, but the examples justify the inclusion. It is concise enough for the tool's complexity, with no unnecessary filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple reference lookup with fully described parameters and safety annotations, the description provides sufficient detail: categories, optional tier filter, return type, and usage examples. Lack of an output schema is acceptable, though more specifics about table format would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with descriptions and enums for both parameters. The description goes further by mapping natural language examples to argument values (e.g., 'What are the Tier III requirements?' -> category=tier_requirements, tier=3), enhancing an agent's understanding of how to construct valid calls.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a clear verb ('look up') and specifies the resource ('data center engineering reference data'), listing four distinct categories. It distinguishes itself from sibling analysis tools by focusing on reference data retrieval, but does not explicitly disambiguate from overlapping tools like dc_assess_tier_classification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Examples show common query patterns, but there is no explicit guidance on when to use this tool versus the sibling analysis tools (dc_calculate_*, dc_analyze_*). The context of 'reference data' implies use for static lookups, yet exclusions are not stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Size UPS systems and battery plants for mission-critical data center facilities. Calculates UPS module count, battery string sizing, floor space, structural load, and 10-year Total Cost of Ownership comparing VRLA vs Lithium-Ion batteries.
Supports all standard redundancy configurations (N, N+1, 2N, 2N+1) and both battery technologies with lifecycle cost analysis including replacement cycles.
Args:
critical_load_kw (number): Critical IT load in kW
redundancy (string): "N", "N+1", "2N", or "2N+1"
runtime_minutes (number): Required battery runtime (5, 10, 15, or 30)
battery_type (string): "VRLA" or "lithium_ion"
ups_efficiency (number): UPS efficiency 0.8-0.99 (default: 0.96)
growth_factor (number): Design growth margin 1.0-2.0 (default: 1.2)
Returns UPS module sizing, battery string count, energy capacity, floor space requirements, weight estimates, 10-year TCO comparison, and recommendations.
Examples:
"Size a 2N UPS with 15 min lithium batteries for 2 MW" -> critical_load_kw: 2000, redundancy: "2N", runtime_minutes: 15, battery_type: "lithium_ion"
"Compare VRLA vs lithium for 500 kW N+1" -> critical_load_kw: 500, redundancy: "N+1", runtime_minutes: 10, battery_type: "VRLA"
| Name | Required | Description | Default |
|---|---|---|---|
| redundancy | Yes | UPS redundancy configuration: N (no redundancy), N+1 (single fault tolerance), 2N (parallel dual), 2N+1 (enhanced parallel) | |
| aging_factor | No | End-of-life aging factor per IEEE 485 practice (default: 1.25 — batteries must meet load at end of life) | |
| battery_type | Yes | Battery technology: VRLA (traditional lead-acid), lithium_ion (LiFePO4 modern) | |
| growth_factor | No | Design growth factor for future expansion (default: 1.2 = 20% growth margin) | |
| ups_efficiency | No | UPS rectifier/inverter efficiency at rated load (default: 0.96 = 96%) | |
| runtime_minutes | Yes | Required UPS battery runtime in minutes (typical: 5-15 min for generator start, 30+ for extended runtime) | |
| critical_load_kw | Yes | Critical IT load requiring UPS protection in kilowatts |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which the description does not contradict. The description adds useful context about what the tool calculates (including lifecycle cost analysis with replacement cycles) and that it returns recommendations, which goes beyond the bare safety annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear opening purpose, followed by Args, Returns, and Examples sections. It is front-loaded and every major section earns its place, though the Args list largely duplicates schema descriptions, making it slightly longer than necessary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there is no output schema, the description adequately explains what the tool returns (UPS module sizing, battery string count, floor space, weight, TCO, recommendations) and covers supported configurations and battery types. The examples further clarify expected parameter usage, making the tool fully usable without external documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Although schema coverage is 100%, the description's Args section adds little beyond the schema and actually introduces a misleading restriction: 'runtime_minutes (5, 10, 15, or 30)' contradicts the schema's range of 5-120. The examples are helpful for mapping natural language to parameters, but the inaccuracy lowers the value added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('Size', 'Calculates') and a defined resource ('UPS systems and battery plants'). It lists concrete outputs (module count, battery string sizing, TCO) and explicitly distinguishes itself from sibling tools like cooling load calculators or generic power redundancy analysis.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description establishes clear usage context by specifying the domain (mission-critical data centers), supported redundancy configurations, battery technologies, and typical runtime values. It does not name alternatives or explicit exclusions, but the focus on UPS/battery sizing is unmistakable compared to siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.1.1dc_analyze_power_redundancydc_analyze_rack_densitydc_assess_tier_classificationdc_calculate_cooling_loaddc_generate_commissioning_plandc_gpu_cooling_optimizerdc_reference_lookupdc_ups_battery_sizingEach tool addresses a distinct data center engineering concern—cooling, power redundancy, tier assessment, commissioning, rack density, GPU cooling, UPS sizing, and reference lookup. There is no semantic overlap that would cause an agent to select the wrong tool.
Most tools follow a verb_noun pattern (dc_calculate_cooling_load, dc_analyze_power_redundancy, dc_generate_commissioning_plan), but three deviate: dc_gpu_cooling_optimizer, dc_ups_battery_sizing, and dc_reference_lookup use noun-based phrasing. This mixed convention undermines predictability.
Eight tools is a well-scoped count for a data center engineering server. Each tool adds meaningful capability, and the set is neither bloated nor too sparse.
The server covers core design and analysis tasks including cooling, power, redundancy, tier classification, commissioning, and GPU-specific cooling. Minor gaps exist (e.g., no energy cost or physical security tools), but the domain is well covered.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
27 engineering compliance and calculation tools for the built environment (UK, EU, UAE).
Design, solve and simulate HVAC systems from real components, weather years and buildings.
AI data-center design engine: size, validate & lay out Rubin-era data centers. Korea live.
AI-callable calculators and engineering models with real formulas. No hallucinated math.
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
