计算平方根
AI agents call sqrt to retrieve information from Math Calculation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a stateless mathematical function that computes and returns a value. It does not create, modify, delete, or execute external operations. Square root calculation is a read-only operation that produces deterministic output from input parameters. Severity is low because misuse (e.g., calculating sqrt of a negative number) has no blast radius beyond a potential error message.
From the tool's definition Tool name 'sqrt' and description '计算平方根' (calculate square root) indicate a pure mathematical computation function that retrieves a result based on input with no side effects, data modification, or external operations.
Attacks that exploit this kind of access
计算平方根. It is categorised as a Read tool in the Math Calculation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Math Calculation MCP Server MCP server in PolicyLayer and add a rule for sqrt: 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 Math Calculation MCP Server. Nothing to install.
sqrt 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 sqrt 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 sqrt. 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.
sqrt is provided by the Math Calculation MCP Server MCP server (k-summer/math_mcps). 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 →