Queue a fresh evaluator run for an active Attrove goal. Returns a run_id immediately (the run is async). To check completion, call attrove_get_goal_status and inspect last_snapshot.evaluator_run_id; once it equals the run_id returned here, the run finished and last_snapshot reflects its output. R...
Part of the Attrove server.
Free to start. No card required.
AI agents invoke attrove_evaluate_goal to trigger processes or run actions in Attrove. 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.
attrove_evaluate_goal 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": {
"attrove_evaluate_goal": {
"limits": [
{
"counter": "attrove_evaluate_goal_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Attrove policy for all 17 tools.
These attack patterns abuse exactly the kind of access attrove_evaluate_goal 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.
Queue a fresh evaluator run for an active Attrove goal. Returns a run_id immediately (the run is async). To check completion, call attrove_get_goal_status and inspect last_snapshot.evaluator_run_id; once it equals the run_id returned here, the run finished and last_snapshot reflects its output. Rate-limited to 6 manual runs per goal per hour.. It is categorised as a Execute tool in the Attrove MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Attrove MCP server in PolicyLayer and add a rule for attrove_evaluate_goal: 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 Attrove. Nothing to install.
attrove_evaluate_goal 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 attrove_evaluate_goal 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 attrove_evaluate_goal. 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.
attrove_evaluate_goal is provided by the Attrove MCP server (@attrove/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 17 Attrove 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.