첫 번째 숫자
AI agents call calculator to retrieve information from TypeScript MCP Server Boilerplate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A calculator tool typically performs arithmetic computations without side effects—a read-like operation that returns results based on input. The description is too minimal to suggest write, execute, or destructive operations.
From the tool's definition Tool name is 'calculator'; description provided is incomplete/uninformative ('첫 번째 숫자' = 'first number' in Korean, which is a fragment). No clear indication of destructive, financial, or execute-level capabilities.
Attacks that exploit this kind of access
첫 번째 숫자. It is categorised as a Read tool in the TypeScript MCP Server Boilerplate MCP Server, which means it retrieves data without modifying state.
Register the TypeScript MCP Server Boilerplate MCP server in PolicyLayer and add a rule for calculator: 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 TypeScript MCP Server Boilerplate. Nothing to install.
calculator 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 calculator 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 calculator. 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.
calculator is provided by the TypeScript MCP Server Boilerplate MCP server (jeena-9595/mcp-server). 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 →