AI agents call nudgeonly_policy to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves guardrail policies without creating, modifying, executing operations, or deleting data. It is explicitly marked as read-only and produces only informational hints. The blast radius of misuse is minimal—it returns policy information that guides behavior but does not itself perform any side effects.
From the tool's definition Tool description explicitly states 'read-only policy' and 'painpoint hints only, no writes, no decisions, no truth-setting'.
Attacks that exploit this kind of access
Return the PinballWake NudgeOnlyAPI guardrails. This is a red-lane, read-only policy for 👉Nudge: painpoint hints only, no writes, no decisions, no truth-setting. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
Register the UnClick MCP server in PolicyLayer and add a rule for nudgeonly_policy: 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 UnClick. Nothing to install.
nudgeonly_policy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the nudgeonly_policy 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 nudgeonly_policy. 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.
nudgeonly_policy is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →