Yamaru Hardware Probe
Expert system hardware probe and performance diagnostic engine for AI, Gaming, and High-Performance workflows. Provides deep system insights such as real-time monitoring, thermal diagnostics, and LLM optimization.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
yamaru-eu
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
analyze_local_systemReads the hardware specifications of the local machine: CPU, RAM, motherboard and OS. Returns a structured JSON object.
analyze_performanceProvides real-time system performance: CPU load, memory usage, and top processes.
analyze_inference_configPerforms a deep scan for LLM inference optimization: GPU details, real memory bandwidth benchmark, ML runtimes (Ollama, Docker, WSL), and environment variables.
get_inference_expert_knowledgeReturns the expert instructions and rules for optimizing LLM inference on this specific hardware. Call this to learn HOW to interpret analyze_inference_config results.
check_llm_compatibility(BETA) Checks if a specific LLM model can run on this machine. Returns optimal quantization and estimated tokens per second. Requires remote API connection.
get_llm_recommendations(BETA) Recommends the best LLM models that can run locally on this machine. Requires remote API connection.
analyze_ram_pressureReports current memory pressure: total/used/free/available memory, swap usage, and top processes by RSS.
check_storage_healthReports per-disk health: type (NVMe/SSD/HDD), vendor, temperature, SMART status, and firmware.
thermal_profileReports current CPU and GPU thermal and frequency state: temperature, utilization, and fan speed.
diagnose_antivirus_impactDetects running antivirus/EDR products and reads their exclusion rules. Checks dev hot paths coverage.
monitor_system_healthMonitors system metrics (CPU load, RAM usage, CPU temperature) over a configurable duration (up to 10 minutes) and returns min/max/avg statistics. Use duration_seconds to set the observation window and interval_seconds to control sampling granularity.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
Command Injection via Unsanitized `locate` Output in `versions()` — systeminformation
systeminformation: OS command injection in networkInterfaces() via interfaces(5) source-directive path on Linux
Systeminformation has a Command Injection via unsanitized interface parameter in wifi.js retry path
Systeminformation has command injection vulnerability in getWindowsIEEE8021x (SSID)
REMOTE_API_URLTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
11/11 tools missing one or more hints — analyze_local_system (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_performance (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_inference_config (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +8 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
Only 2/11 tools referenced in tests (18%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 7 high severity in production deps — @modelcontextprotocol/sdk@1.0.0 (high), systeminformation@5.23.5 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/yamaru-eu/hardware-probe)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check