AI agents invoke calculate to trigger actions in FastMCP Multi-Tenancy. 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 is named 'calculate' and described only as 'Perform a calculation', which suggests computational execution rather than simple data retrieval or mutation. However, the description is extremely sparse, so the exact nature of the calculation (e.g., arithmetic, arbitrary code evaluation, or financial computation) is unknown.
From the tool's definition Tool name 'calculate' and description 'Perform a calculation' — description is minimal and uninformative about scope or side effects.
Documented attack patterns abuse exactly the kind of access calculate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FastMCP Multi-Tenancy, and nothing reaches the server without passing your rules. This is the rule we recommend for calculate:
{
"version": "1",
"default": "deny",
"tools": {
"calculate": {
"limits": [
{
"counter": "calculate_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}calculate 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.
Perform a calculation. It is categorised as a Execute tool in the FastMCP Multi-Tenancy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FastMCP Multi-Tenancy MCP server in PolicyLayer and add a rule for calculate: 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 FastMCP Multi-Tenancy. Nothing to install.
calculate 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 calculate 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 calculate. 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.
calculate is provided by the FastMCP Multi-Tenancy MCP server (timothywangdev/mcptoolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FastMCP Multi-Tenancy, 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.
4 FastMCP Multi-Tenancy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.