performance_metrics

THE RISK

Low Risk

Why performance_metrics needs a policy

The tool description 'Get performance metrics' indicates a read-only operation that fetches runtime or system performance data. No writes, executions, or destructive actions are implied. Low severity as misuse would only expose internal metrics.

From the tool's definition 'Get performance metrics' — retrieves/queries diagnostic data with no side effects

Documented attack patterns abuse exactly the kind of access performance_metrics gives an agent:

POLICY

How to control performance_metrics

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Mathematics, and nothing reaches the server without passing your rules. This is the rule we recommend for performance_metrics:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "performance_metrics": {}
  }
}

performance_metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register MCP Mathematics — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Mathematics tools

Destructive clear_history Clear history Destructive delete_session Delete session Execute batch_calculate Batch calculate expressions Execute calculate_expression Evaluate math expression Execute matrix_operation matrix_operation Execute optimize_memory Optimize memory Execute session_calculate Session calculation Execute convert_natural_language Natural language conversion

All 18 MCP Mathematics tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about performance_metrics

What does the performance_metrics tool do? +

Get performance metrics. It is categorised as a Read tool in the MCP Mathematics MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on performance_metrics? +

Register the MCP Mathematics MCP server in PolicyLayer and add a rule for performance_metrics: 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 MCP Mathematics. Nothing to install.

What risk level is performance_metrics? +

performance_metrics is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit performance_metrics? +

Yes. Add a rate_limit block to the performance_metrics 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.

How do I block performance_metrics completely? +

Set action: deny in the PolicyLayer policy for performance_metrics. 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.

What MCP server provides performance_metrics? +

performance_metrics is provided by the MCP Mathematics MCP server (shsharkar/mcp-mathematics). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Mathematics tool call.

Start from MCP Mathematics, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →