Run baseline plus counterfactual variants and measure verdict/score sensitivity.
Part of the WaveGuard server.
Free to start. No card required.
AI agents invoke waveguard_counterfactual to trigger processes or run actions in WaveGuard. 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.
waveguard_counterfactual 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": {
"waveguard_counterfactual": {
"limits": [
{
"counter": "waveguard_counterfactual_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full WaveGuard policy for all 19 tools.
These attack patterns abuse exactly the kind of access waveguard_counterfactual 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 baseline plus counterfactual variants and measure verdict/score sensitivity.. It is categorised as a Execute tool in the WaveGuard MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the WaveGuard MCP server in PolicyLayer and add a rule for waveguard_counterfactual: 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 WaveGuard. Nothing to install.
waveguard_counterfactual 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 waveguard_counterfactual 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 waveguard_counterfactual. 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.
waveguard_counterfactual is provided by the WaveGuard MCP server (https://gpartin--waveguard-api-fastapi-app.modal.run/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 19 WaveGuard 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.