Run a live A/B test against the engine's TOP 3 PICKS for a stated purpose — the engine chooses the candidates from the full catalog. Generates 5 representative test queries (auto-expands to 10 or 15 if results are too close to call), runs them through the picked models in parallel, and returns re...
Part of the XFMS — Model Source server.
Free to start. No card required.
AI agents invoke benchmark to trigger processes or run actions in XFMS — Model Source. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
benchmark can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"benchmark": {
"limits": [
{
"counter": "benchmark_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full XFMS — Model Source policy for all 5 tools.
These attack patterns abuse exactly the kind of access benchmark gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run a live A/B test against the engine's TOP 3 PICKS for a stated purpose — the engine chooses the candidates from the full catalog. Generates 5 representative test queries (auto-expands to 10 or 15 if results are too close to call), runs them through the picked models in parallel, and returns real cost, latency, and plain-English commentary on who won what. Use AFTER pick or rank when the user wants the engine's own picks stress-tested with live data. DO NOT use this when the user has already named specific candidate models — the engine will ignore the names and test its own picks. Use compare instead in that case. Costs more than rank (15+ live LLM calls).. It is categorised as a Execute tool in the XFMS — Model Source MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the XFMS — Model Source 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 XFMS — Model Source. 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 XFMS — Model Source MCP server (https://xfms.vercel.app/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 XFMS — Model Source 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.