Compare performance between two time periods.
AI agents call compare_periods to retrieve information from PropellerAds MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and compares historical performance metrics across time periods. It does not create, modify, delete, or execute any actions on campaigns or data. It is a read-only analytical function that fits the 'Read' category for retrieving or querying data without side effects.
From the tool's definition The tool name is 'compare_periods' and the description states it 'Compare[s] performance between two time periods.' This is purely a data retrieval and analysis operation with no side effects.
Attacks that exploit this kind of access
Compare performance between two time periods. It is categorised as a Read tool in the PropellerAds MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PropellerAds MCP Server MCP server in PolicyLayer and add a rule for compare_periods: 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 PropellerAds MCP Server. Nothing to install.
compare_periods 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 compare_periods 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 compare_periods. 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.
compare_periods is provided by the PropellerAds MCP Server MCP server (jannafta/propellerads-mcp). 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 →