calculate_percentage
AI agents call calculate_percentage to retrieve information from MCP Multi-Tool Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the server context (calculator tools for mathematical operations) and the tool name, this almost certainly performs a read-only percentage calculation with no side effects. However, the empty description lowers confidence. Severity is low as mathematical computations pose minimal blast radius.
From the tool's definition Tool name 'calculate_percentage' suggests a mathematical computation; description is empty and uninformative.
Attacks that exploit this kind of access
calculate_percentage. It is categorised as a Read tool in the MCP Multi-Tool Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Multi-Tool Server MCP server in PolicyLayer and add a rule for calculate_percentage: 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 MCP Multi-Tool Server. Nothing to install.
calculate_percentage 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 calculate_percentage 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 calculate_percentage. 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.
calculate_percentage is provided by the MCP Multi-Tool Server MCP server (xiaoyuchenhot/mcp-example). 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 →