AI agents invoke calculate to trigger actions in Demo. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Evaluating math expressions can range from safe arithmetic to arbitrary code execution (e.g., via eval()). The description is minimal and does not specify sandboxing. Given the context of a demo server with simple tools (add, get_weather, greet), it is likely a basic calculator, but the risk of unsandboxed expression evaluation warrants Execute classification at medium severity.
From the tool's definition '计算数学表达式' (calculate math expression) — evaluates an expression, which depending on implementation could execute arbitrary code
Attacks that exploit this kind of access
计算数学表达式。. It is categorised as a Execute tool in the Demo MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Demo MCP server in PolicyLayer and add a rule for calculate: 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 Demo. Nothing to install.
calculate is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the calculate 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. 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 is provided by the Demo MCP server (liuyuyan6100/mcp-server-demo). 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 →