Add two numbers together
AI agents call add_numbers to retrieve information from MCPServer (FastMCP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple mathematical addition of two numbers. It is a pure function with no side effects, no data read from external sources, no writes, and no execution of commands. It falls closest to 'Read' as a data-processing/query operation, though it is essentially stateless computation. Misuse potential is negligible.
From the tool's definition 'Add two numbers together' — pure arithmetic computation with no side effects, no data modification, no external operations
Attacks that exploit this kind of access
Add two numbers together. It is categorised as a Read tool in the MCPServer (FastMCP) MCP Server, which means it retrieves data without modifying state.
Register the MCPServer (FastMCP) MCP server in PolicyLayer and add a rule for add_numbers: 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 MCPServer (FastMCP). Nothing to install.
add_numbers 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 add_numbers 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 add_numbers. 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.
add_numbers is provided by the MCPServer (FastMCP) MCP server (justineqinlao/mcpserver). 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 →