AI agents call igniteonly_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.
The tool appears to fetch and return policy or configuration guardrails for the IgniteOnlyAPI. This is a read/query operation with no apparent side effects. The description explicitly states it returns guardrails and excludes build, merge, approval, closure, or truth-setting actions. Confidence is moderate because the description is somewhat opaque and domain-specific, making the full scope unclear.
From the tool's definition 'Return the PinballWake IgniteOnlyAPI guardrails' — the tool returns/retrieves policy/guardrail information
Attacks that exploit this kind of access
Return the PinballWake IgniteOnlyAPI guardrails. This is the green ignite sibling to NudgeOnly: verified worker wake packets only, no build, merge, approval, closure, or 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 igniteonly_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.
igniteonly_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 igniteonly_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 igniteonly_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.
igniteonly_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 →