Free research preview — get a quick summary, 2 key facts, and confidence score for any query. No payment required. Use this to test queries before committing to a paid research call. Rate limited to 10/hour.
AI agents call preview to retrieve information from Agentoracle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though preview only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Free research preview — get a quick summary, 2 key facts, and confidence score for any query. No payment required. Use this to test queries before committing to a paid research call. Rate limited to 10/hour. It is categorised as a Read tool in the Agentoracle MCP Server, which means it retrieves data without modifying state.
Register the Agentoracle MCP server in PolicyLayer and add a rule for preview: 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 Agentoracle. Nothing to install.
preview 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 preview 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 preview. 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.
preview is provided by the Agentoracle MCP server (tkcollective/agentoracle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.