格式化数字
AI agents call format_number 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.
Formatting a number is a pure computational operation with no state changes, data persistence modifications, or external effects. It retrieves no sensitive data beyond what the user has already computed, and cannot delete, execute arbitrary code, or affect financial systems. This is a safe read-category tool with minimal risk if misused by an AI agent.
From the tool's definition The tool name 'format_number' and description '格式化数字' (format number in Chinese) indicate a function that formats or displays numerical output.
Attacks that exploit this kind of access
格式化数字. 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 format_number: 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.
format_number 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 format_number 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 format_number. 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.
format_number 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 →