Silicon Analysts

get_accelerator_costs

Read-onlyIdempotent

Returns 18 AI accelerators (H100/H200/B100/B200/GB200/GB300/Rubin, MI300X/MI355X/MI455X, Gaudi 3, TPU v5p/v6e, Trainium 2/3, Maia 100, MTIA v2) with structured fields: chip, vendor, processNode, dieSizeMm2, memoryType, memoryCapacityGb, memoryBandwidthTbS, fp8TflopsSparse, bf16TflopsDense, packageType, estMfgCostUsd, estSellPriceUsd, chipGrossMarginPct, costBreakdown.{logicDie, hbm, packaging, testAssembly}, interconnect.

USE THIS for: comparing manufacturing cost or sell price across vendors; looking up published specs of a current accelerator (includes early-ramp 2026 parts like Rubin and MI455X, flagged via provenance.confidence_tier).

DO NOT USE for: chips not in the catalog (use get_market_pulse for market news/forecasts); custom chip cost modeling (use calculate_chip_cost); HBM market dynamics (use get_hbm_market_data).

Filters: vendor (enum), chip (substring match), fields (projection list). Returns empty array if filters match nothing — does not error. Each chip record carries provenance.last_updated; data refreshes monthly.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`chip`	No
`fields`	No
`vendor`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedMay 31, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Description adds significant context beyond annotations: lists 18 specific chip names, explains filter behavior (empty array on no match, not an error), mentions provenance.confidence_tier for early-ramp parts, and states data refreshes monthly. Annotations already declare readOnlyHint and idempotentHint, but the description deepens disclosure with concrete behavioral traits.

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?

Front-loaded with the core purpose in first sentence. Use cases and filter section separated clearly. Every sentence adds unique value with no redundancy.

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?

Despite no output schema, the description enumerates all 18 chips, lists all fields and structures, and documents filter behavior and data provenance. It's complete for agent decision-making, covering scope, edge cases, and data freshness.

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

Parameters4/5

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

Schema coverage is 0%, so description carries full burden. It explains vendor (enum), chip (substring match), and fields (projection list) with behavioral details. However, it could add value by describing valid field names or projection syntax beyond what the schema implies.

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 explicitly names the resource (18 AI accelerators) and the action (returns structured fields with cost breakdowns and specs). It differentiates from siblings by listing what each chip is and by stating DO NOT USE for other tools like get_market_pulse and calculate_chip_cost.

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

Usage Guidelines5/5

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

Clearly states USE THIS for comparing costs/specs across vendors and DO NOT USE for chips not in catalog (use get_market_pulse), custom chip cost modeling (use calculate_chip_cost), or HBM market data (use get_hbm_market_data). This is explicit when-to and when-not-to guidance with relevant alternatives.

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

All Silicon Analysts tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation3/5

Several tools overlap in domain and purpose, such as get_market_pulse vs get_market_intelligence and get_wafer_pricing vs get_foundry_economics. The detailed USE/DO NOT USE sections help, but the tool names alone do not always make the distinction obvious, requiring careful reading to avoid misselection.

Naming Consistency4/5

18 of 20 tools follow a consistent get_<noun> pattern, with calculate_chip_cost and estimate_lead_time as minor deviations. No chaotic mixing of camelCase or inconsistent verb styles; the overall scheme is predictable and readable.

Tool Count4/5

20 tools is slightly above the ideal 3-15 range but reasonable for the server's broad scope covering cost modeling, capacity, allocation, HBM, policy, and market intelligence. Each tool has a distinct niche, though a few could potentially be consolidated.

Completeness4/5

The server provides comprehensive coverage of semiconductor cost estimation, market data, fab capacity, allocation, HBM qualification, and policy timelines. Minor gaps exist (e.g., no dedicated memory pricing tool or general search), but these are covered through get_market_dataset and other tools; there are no critical missing functions for the stated domain.

Resources

Need Help?