Submit benchmark answers for scoring.
Risk signalsHandles credentials or secrets (api_key)
Part of the A2ABench server.
Free to start. No card required.
AI agents use submit_benchmark_run to create or modify resources in A2ABench. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call submit_benchmark_run repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach A2ABench.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"submit_benchmark_run": {
"limits": [
{
"counter": "submit_benchmark_run_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full A2ABench policy for all 3 tools.
These attack patterns abuse exactly the kind of access submit_benchmark_run gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Submit benchmark answers for scoring.. It is categorised as a Write tool in the A2ABench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the A2ABench MCP server in PolicyLayer and add a rule for submit_benchmark_run: 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 A2ABench. Nothing to install.
submit_benchmark_run is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the submit_benchmark_run 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 submit_benchmark_run. 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.
submit_benchmark_run is provided by the A2ABench MCP server (@khalidsaidi/a2abench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 A2ABench tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.