Use the expr-eval library to evaluate the input mathematical expression and return the result.
AI agents invoke cal to trigger actions in Cal Server. 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 evaluates arbitrary mathematical expressions via a library (expr-eval), which constitutes code/expression execution. While the library is sandboxed to math operations, expression evaluators can sometimes be abused for unintended computations or resource exhaustion.
From the tool's definition 'evaluate the input mathematical expression' using 'expr-eval library' — runs/executes arbitrary user-supplied expressions through an evaluation engine
Documented attack patterns abuse exactly the kind of access cal gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cal Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cal:
{
"version": "1",
"default": "deny",
"tools": {
"cal": {
"limits": [
{
"counter": "cal_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}cal 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.
Use the expr-eval library to evaluate the input mathematical expression and return the result. It is categorised as a Execute tool in the Cal Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cal Server MCP server in PolicyLayer and add a rule for cal: 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 Cal Server. Nothing to install.
cal 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 cal 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 cal. 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.
cal is provided by the Cal Server MCP server (pwh-pwh/cal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cal Server, 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 Cal Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.