Returns 13 specific AI accelerators (H100/H200/B100/B200/GB200, MI300X/MI355X, Gaudi 3, TPU v5p, Trainium 2, Maia 100, MTIA v2) with structured fields: chip, vendor, processNode, dieSizeMm2, memoryType, memoryCapacityGb, memoryBandwidthTbS, fp8TflopsSparse, bf16TflopsDense, packageType, estMfgCos...
Part of the Silicon Analysts server.
Free to start. No card required.
AI agents call get_accelerator_costs to retrieve information from Silicon Analysts without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_accelerator_costs only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"get_accelerator_costs": {}
}
}See the full Silicon Analysts policy for all 6 tools.
These attack patterns abuse exactly the kind of access get_accelerator_costs gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Returns 13 specific AI accelerators (H100/H200/B100/B200/GB200, MI300X/MI355X, Gaudi 3, TPU v5p, Trainium 2, 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 specific shipping accelerator. DO NOT USE for: chips not yet shipping (use get_market_pulse for 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.. It is categorised as a Read tool in the Silicon Analysts MCP Server, which means it retrieves data without modifying state.
Register the Silicon Analysts MCP server in PolicyLayer and add a rule for get_accelerator_costs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Silicon Analysts. Nothing to install.
get_accelerator_costs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_accelerator_costs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_accelerator_costs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_accelerator_costs is provided by the Silicon Analysts MCP server (https://siliconanalysts.com/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Silicon Analysts tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.