list_benchmark_questions

// WHEN AGENTS USE THIS TOOL

AI agents call list_benchmark_questions to retrieve information from A2ABench without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though list_benchmark_questions only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

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

See the full A2ABench policy for all 3 tools.

// MORE A2ABENCH TOOLS

// WHAT CAN GO WRONG

These attack patterns abuse exactly the kind of access list_benchmark_questions gives an agent. Each links to the full case and the policy that stops it:

• Prompt Injection via Tool Results
• Indirect Prompt Injection
• Credential leak via error messages

Browse the full MCP Attack Database →

// OTHER READ TOOLS

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

// RELATED READING

• Rate Limiting MCP Tool Calls: A Practical Guide
• MCP Security: Why Prompt Guardrails Aren't Enough
• The Case for Deterministic AI Agent Policies
• Why AI Agents Need a Control Plane

// FAQ