Tell ClarifyPrompt whether an optimization
Part of the Clarifyprompt server.
Free to start. No card required.
AI agents use save_outcome to create or modify resources in Clarifyprompt. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call save_outcome repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Clarifyprompt.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"save_outcome": {
"limits": [
{
"counter": "save_outcome_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Clarifyprompt policy for all 28 tools.
These attack patterns abuse exactly the kind of access save_outcome gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Tell ClarifyPrompt whether an optimization. It is categorised as a Write tool in the Clarifyprompt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Clarifyprompt MCP server in PolicyLayer and add a rule for save_outcome: 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 Clarifyprompt. Nothing to install.
save_outcome is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_outcome 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 save_outcome. 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.
save_outcome is provided by the Clarifyprompt MCP server (clarifyprompt-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 Clarifyprompt 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.