AI agents call get_aws_reference to retrieve information from Tok without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and displays AWS Well-Architected framework reference patterns. It performs information retrieval to inform architecture design decisions, with no capability to modify, execute, delete, or commit financial resources. No arguments suggest external system effects beyond returning architectural guidance data.
From the tool's definition Tool retrieves AWS reference architectures and patterns based on service type and scale. The description indicates it 'queries' (조회합니다) and 'provides' (제공합니다) architectural patterns—read-only operations with no side effects.
Attacks that exploit this kind of access
AWS 모범 사례 아키텍처를 조회합니다. 서비스 유형과 규모에 맞는 AWS Well-Architected 기반 아키텍처 패턴을 제공합니다. It is categorised as a Read tool in the Tok MCP Server, which means it retrieves data without modifying state.
Register the Tok MCP server in PolicyLayer and add a rule for get_aws_reference: 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 Tok. Nothing to install.
get_aws_reference 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 get_aws_reference 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 get_aws_reference. 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.
get_aws_reference is provided by the Tok MCP server (seongminjaden/tok_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 →