analyze-query-performance · MCP Firebird MCP: Risk & Policy

WHAT IT DOES

What analyze-query-performance does on MCP Firebird

AI agents invoke analyze-query-performance to trigger actions in MCP Firebird. 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.

WHY IT NEEDS A POLICY

Why analyze-query-performance needs a policy

This tool actually executes a SQL query multiple times against the database. Since it runs arbitrary SQL, it could execute DML or DDL statements repeatedly, amplifying any side effects. The repeated execution aspect increases blast radius significantly — a destructive or expensive query run multiple times could cause serious damage or performance degradation.

From the tool's definition 'Analyzes the performance of a SQL query by executing it multiple times and measuring execution time'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

analyze-query-performance Rate-limited

analyze-query-performance 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "analyze-query-performance": {
      "limits": [
        {
          "counter": "analyze-query-performance_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Firebird, so you can run agents against it safely.

FAQ

Questions about analyze-query-performance

What does the analyze-query-performance tool do? +

Analyzes the performance of a SQL query by executing it multiple times and measuring execution time. It is categorised as a Execute tool in the MCP Firebird MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on analyze-query-performance? +

Register the MCP Firebird MCP server in PolicyLayer and add a rule for analyze-query-performance: 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 Firebird. Nothing to install.

What risk level is analyze-query-performance? +

analyze-query-performance is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit analyze-query-performance? +

Yes. Add a rate_limit block to the analyze-query-performance 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 analyze-query-performance completely? +

Set action: deny in the PolicyLayer policy for analyze-query-performance. 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 analyze-query-performance? +

analyze-query-performance is provided by the MCP Firebird MCP server (luancamara/mcpfirebird). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.