AI agents invoke calculator to trigger actions in Xiaozhi. 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.
The tool evaluates Python expressions at runtime. While it mentions math/random, executing arbitrary expressions could allow unintended code paths. It is not a simple read or write; it runs code, placing it in Execute. Severity is medium because math/random access is somewhat limited, but arbitrary expression evaluation carries inherent risk.
From the tool's definition 'calculate the result of a python expression' — executes arbitrary Python expressions with access to math and random modules
Attacks that exploit this kind of access
For mathamatical calculation, always use this tool to calculate the result of a python expression. You can use 'math' or 'random' directly, without 'import'. It is categorised as a Execute tool in the Xiaozhi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xiaozhi 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 Xiaozhi. Nothing to install.
calculator 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 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 Xiaozhi MCP server (zhouhaojiang/xiaozhi-mcp). 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 →