AI agents call compare_templates to retrieve information from Moengage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Comparison operations are inherently non-destructive and non-modifying. Even if the tool retrieves template data for comparison purposes, it produces no side effects. The empty description reduces confidence slightly, but the semantic meaning of 'compare' and the presence of other read tools on the server (analyze_template, get_campaign_stats, get_personalized_preview) support a Read classification.
From the tool's definition Tool name 'compare_templates' suggests a read-only comparison operation. Description is empty, limiting direct evidence, but the verb 'compare' typically implies retrieval and analysis of existing data without modification.
Attacks that exploit this kind of access
compare_templates. It is categorised as a Read tool in the Moengage MCP Server, which means it retrieves data without modifying state.
Register the Moengage MCP server in PolicyLayer and add a rule for compare_templates: 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 Moengage. Nothing to install.
compare_templates 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_templates 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_templates. 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_templates is provided by the Moengage MCP server (poddubnyoleg/moengage_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 →