Returns the expert instructions and rules for optimizing LLM inference on this specific hardware. Call this to learn HOW to interpret analyze_inference_config results.
AI agents call get_inference_expert_knowledge to retrieve information from Hardware Probe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves informational content (expert knowledge, instructions, rules) for educational/interpretive purposes. It has no side effects, does not execute commands, does not modify data, and does not access sensitive operations. It is purely a Read operation with minimal risk—the information returned is intended to help users understand diagnostic results.
From the tool's definition Tool returns expert instructions and rules for interpreting LLM inference configuration analysis results. The name includes 'get' and description uses 'Returns', indicating data retrieval with no modification or execution of external operations.
Documented attack patterns abuse exactly the kind of access get_inference_expert_knowledge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Hardware Probe, and nothing reaches the server without passing your rules. This is the rule we recommend for get_inference_expert_knowledge:
{
"version": "1",
"default": "deny",
"tools": {
"get_inference_expert_knowledge": {}
}
}get_inference_expert_knowledge is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Returns the expert instructions and rules for optimizing LLM inference on this specific hardware. Call this to learn HOW to interpret analyze_inference_config results. It is categorised as a Read tool in the Hardware Probe MCP Server, which means it retrieves data without modifying state.
Register the Hardware Probe MCP server in PolicyLayer and add a rule for get_inference_expert_knowledge: 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 Hardware Probe. Nothing to install.
get_inference_expert_knowledge 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_inference_expert_knowledge 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_inference_expert_knowledge. 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_inference_expert_knowledge is provided by the Hardware Probe MCP server (@yamaru-eu/hardware-probe). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Hardware Probe, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
11 Hardware Probe tools catalogued and risk-classified — across an index of 43,000+ MCP servers.