performance_compare

Compare current performance against a saved baseline. Returns PASS/FAIL per metric with thresholds.

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/performance-compare.md

WHAT IT DOES

What performance_compare does on Claude Mobile

AI agents call performance_compare to retrieve information from Claude Mobile without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why performance_compare is rated Low

This tool reads and compares performance metrics against a baseline, returning results. It does not modify, delete, or execute anything — it's purely analytical/read-only. The only uncertainty is whether 'saving' a baseline is part of this tool's scope, but the description focuses on comparison and returning results.

From the tool's definition Compare current performance against a saved baseline. Returns PASS/FAIL per metric with thresholds.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs performance_compare safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For performance_compare, this is the rule to start with:

performance_compare Allowed

performance_compare is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every performance_compare call is checked against it from then on.

FAQ

Questions about performance_compare

What does the performance_compare tool do? +

Compare current performance against a saved baseline. Returns PASS/FAIL per metric with thresholds. It is categorised as a Read tool in the Claude Mobile MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on performance_compare? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for performance_compare: 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 Claude Mobile. Nothing to install.

What risk level is performance_compare? +

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

Can I rate-limit performance_compare? +

Yes. Add a rate_limit block to the performance_compare 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_compare completely? +

Set action: deny in the PolicyLayer policy for performance_compare. 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_compare? +

performance_compare is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →