AI agents invoke add to trigger actions in Calculator MCP. 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.
Although addition is a simple arithmetic operation with no data persistence or side effects, it fits 'Execute' as it runs a computation/operation rather than reading existing data or writing/modifying stored data. However, the blast radius is very low since it only returns a computed numeric result with no external effects. It cannot cause financial, destructive, or write-side-effect harm.
From the tool's definition 'Add two numbers' — performs a mathematical operation (addition) by executing a computation
Documented attack patterns abuse exactly the kind of access add gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Calculator MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add:
{
"version": "1",
"default": "deny",
"tools": {
"add": {
"limits": [
{
"counter": "add_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}add stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add two numbers. It is categorised as a Execute tool in the Calculator MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Calculator 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 Calculator MCP. Nothing to install.
add 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 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 Calculator MCP server (wrtnlabs/calculator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Calculator MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Calculator MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.