Run a performance benchmark against the vLLM server using GuideLLM
AI agents invoke run_benchmark to trigger actions in vLLM MCP Server. 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 executes an external benchmarking utility (GuideLLM) against a vLLM server. While benchmarking itself is not inherently destructive, it is an Execute-category action because it triggers external operations and generates load/side effects on the server.
From the tool's definition Tool name is 'run_benchmark' and description states it will 'Run a performance benchmark against the vLLM server using GuideLLM'.
Documented attack patterns abuse exactly the kind of access run_benchmark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and vLLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_benchmark:
{
"version": "1",
"default": "deny",
"tools": {
"run_benchmark": {
"limits": [
{
"counter": "run_benchmark_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_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.
Run a performance benchmark against the vLLM server using GuideLLM. It is categorised as a Execute tool in the vLLM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the vLLM MCP Server MCP server in PolicyLayer and add a rule for run_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 vLLM MCP Server. Nothing to install.
run_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 run_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 run_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.
run_benchmark is provided by the vLLM MCP Server MCP server (micytao/vllm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from vLLM MCP Server, 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.
12 vLLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.