AI agents call add to retrieve information from Small without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a stateless arithmetic operation, returning the sum of two inputs. It reads/computes data without modifying any state, triggering external operations, or causing any side effects. Misuse potential is negligible.
From the tool's definition "Add two numbers and return the result" — pure arithmetic computation with no side effects
Attacks that exploit this kind of access
Add two numbers and return the result. It is categorised as a Read tool in the Small MCP Server, which means it retrieves data without modifying state.
Register the Small MCP server in PolicyLayer and add a rule for add: 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 Small. Nothing to install.
add 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 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. 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 is provided by the Small MCP server (nishant-iit/smallmp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
add is one line of Small's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →