Subtracts the second number from the first.
AI agents call calculate_subtract to retrieve information from Calculator without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a mathematical operation that retrieves a computed result without modifying any state, creating data, executing commands, deleting anything, or involving financial transactions. It matches the Read category profile of stateless query operations, albeit mathematical rather than database-oriented. Severity is low because misuse cannot cause harm beyond incorrect calculations.
From the tool's definition Tool performs arithmetic subtraction: 'Subtracts the second number from the first.' No side effects, no data modification, no external operations—purely computational.
Attacks that exploit this kind of access
Subtracts the second number from the first. It is categorised as a Read tool in the Calculator MCP Server, which means it retrieves data without modifying state.
Register the Calculator MCP server in PolicyLayer and add a rule for calculate_subtract: 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 Calculator. Nothing to install.
calculate_subtract 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_subtract 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_subtract. 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_subtract is provided by the Calculator MCP server (mvavassori/calculator-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 →