AI agents call recommend_cpu_arch 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 analyzes workload characteristics and returns recommendations for CPU architecture selection (ARM vs x86). It is purely advisory and informational with no side effects. No data is created, modified, deleted, or executed. No financial transactions occur. This is clearly a Read operation—querying/analyzing input to provide guidance without altering any system state.
From the tool's definition Tool name 'recommend_cpu_arch' and description indicating it 'recommends optimal CPU architecture' based on workload characteristics, considering cost efficiency and performance.
Attacks that exploit this kind of access
워크로드 특성에 따라 최적의 CPU 아키텍처(ARM/x86)를 추천합니다. 비용 효율성과 성능을 고려한 추천을 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 recommend_cpu_arch: 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.
recommend_cpu_arch 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 recommend_cpu_arch 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 recommend_cpu_arch. 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.
recommend_cpu_arch 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 →