Measure DMA read/write throughput in MB/s. Use this to verify the FPGA device
AI agents invoke benchmark to trigger actions in Nevercheese Pcileech Memprocfs. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool actively performs DMA read/write operations against hardware to measure throughput. It triggers real hardware I/O operations (DMA transfers) whose effects depend on the FPGA device state. While primarily diagnostic, it executes actual memory transfers against physical hardware, placing it in the Execute category. Misuse could destabilize the DMA device or interfere with ongoing memory operations.
From the tool's definition Measure DMA read/write throughput in MB/s. Use this to verify the FPGA device
Documented attack patterns abuse exactly the kind of access benchmark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nevercheese Pcileech Memprocfs, and nothing reaches the server without passing your rules. This is the rule we recommend for benchmark:
{
"version": "1",
"default": "deny",
"tools": {
"benchmark": {
"limits": [
{
"counter": "benchmark_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}benchmark stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Measure DMA read/write throughput in MB/s. Use this to verify the FPGA device. It is categorised as a Execute tool in the Nevercheese Pcileech Memprocfs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nevercheese Pcileech Memprocfs MCP server in PolicyLayer and add a rule for benchmark: 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 Nevercheese Pcileech Memprocfs. Nothing to install.
benchmark is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the benchmark 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 benchmark. 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.
benchmark is provided by the Nevercheese Pcileech Memprocfs MCP server (neverdecel/nevercheese-pcileech-memprocfs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nevercheese Pcileech Memprocfs, 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.
37 Nevercheese Pcileech Memprocfs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.