Aguasto Engineering Calculators
Server Details
Educational model-memory, facility-energy and completed-token cost calculations.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: facility energy, token cost, weight memory, and GPU access information. No two tools overlap in inputs or outputs, so an agent can select the right one unambiguously.
Three calculators follow a consistent noun_noun pattern (facility_energy, token_cost, weight_memory), while get_gpu_early_access uses a verb_noun form. The deviation is minor and still readable, but it breaks full consistency.
Four tools is a well-scoped set for a calculator server; each tool covers a distinct calculation or access need without bloat. There are no redundant or trivial entries.
The set covers facility energy, token economics, and weight memory, but misses other common engineering dimensions such as performance/throughput, cluster sizing, or broader TCO. get_gpu_early_access is useful but not a calculator, so the calculator surface has notable gaps.
Available Tools
4 toolsfacility_energyBRead-onlyIdempotentInspect
Use this tool to model a facility energy scenario. Returns PUE-adjusted facility power in kW, energy in kWh and illustrative electricity cost in USD.
Inputs: pue (required), hours (required), it_kw (required), usd_per_kwh (required). Returns: inputs, result, calculation, limitations
get_gpu_early_accessARead-onlyIdempotentInspect
Use this tool to guide a customer who wants to request GPU capacity. Returns the current early-access terms and official Aguasto Console links for account creation, sign-in and capacity requests.
Inputs: no named parameters. Returns: review, status, loginUrl, requestUrl, +2 more
token_costARead-onlyIdempotentInspect
Use this tool to compare the unit economics of inference scenarios. Returns an illustrative cost in USD per million completed tokens from your cost and output assumptions.
Inputs: cost_usd (required), completed_tokens (required). Returns: inputs, result, calculation, limitations
weight_memoryARead-onlyIdempotentInspect
Use this tool to compare weight precision assumptions. Returns model weight memory in decimal GB and binary GiB, excluding KV cache, activations and runtime overhead.
Inputs: bits (required), parameters_billions (required). Returns: inputs, result, calculation, limitations
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
LLM pricing, provider and gateway rates, pricing tiers, and inference cost calculations.
LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.
LLM prices, cost estimates and break-even, plus your app's AI cost and margin per user.
Real cost per AI result, LLM prices, switch costs, shutdown dates, A/B test sizes and judge checks.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables precise financial analysis of AI agent costs, including token pricing, multi-step run estimates, model comparison, and ROI versus human labor, with deterministic decimal math.-
- AlicenseNot gradedqualityCmaintenanceToken cost math for LLM API calls: current per-million-token rates for 69 models across 17 providers, with local arithmetic for estimates, comparisons and monthly budgets. Rates are verified and date-stamped.57 npm2MIT

OptimToken MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to fetch live, dated prices for LLM models and cloud compute instances across providers, compare and recommend models, and estimate monthly costs based on workload-specific token shapes and constraints.MIT- AlicenseAqualityBmaintenanceLLM API prices, cost estimates, model comparisons and language token tax for GPT, Claude and Gemini.7170 PyPIMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.