AI agents call policy_get to retrieve information from Amazon Translate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to retrieve or fetch policy information based on its name (get suffix), which aligns with Read operations that have no side effects. However, the empty description significantly reduces confidence in this classification. The term 'policy' in the context of AWS could refer to IAM policies or service policies, but 'get' operations are non-destructive reads.
From the tool's definition Tool name 'policy_get' suggests retrieval of policy data. Description is empty, limiting certainty.
Documented attack patterns abuse exactly the kind of access policy_get gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon Translate MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for policy_get:
{
"version": "1",
"default": "deny",
"tools": {
"policy_get": {}
}
} policy_get is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
policy_get. It is categorised as a Read tool in the Amazon Translate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon Translate MCP Server MCP server in PolicyLayer and add a rule for policy_get: 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 Amazon Translate MCP Server. Nothing to install.
policy_get 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 policy_get 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 policy_get. 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.
policy_get is provided by the Amazon Translate MCP Server MCP server (awslabs.amazon-translate-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amazon Translate MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
805 Amazon Translate MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.