generate_qa_dataset · RAGScore MCP: Risk & Policy

WHAT IT DOES

What generate_qa_dataset does on RAGScore

AI agents use generate_qa_dataset to create or update resources in RAGScore — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RAGScore environment.

WHY IT NEEDS A POLICY

Why generate_qa_dataset needs a policy

Creates new datasets which are reversible writes to the system's data store. Not destructive (can be regenerated), not execute (no arbitrary code/commands), not read-only (modifies state). Medium severity because a malicious actor could generate large volumes of poor-quality data to pollute the evaluation system or waste resources, but impacts are recoverable.

From the tool's definition Tool named 'generate_qa_dataset' with empty description; based on name and sibling tools (evaluate_rag, get_corrections, quick_test_rag) on a RAG evaluation server, this tool creates new QA datasets.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_qa_dataset Rate-limited

generate_qa_dataset stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_qa_dataset": {
      "limits": [
        {
          "counter": "generate_qa_dataset_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about generate_qa_dataset

What does the generate_qa_dataset tool do? +

generate_qa_dataset. It is categorised as a Write tool in the RAGScore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_qa_dataset? +

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

What risk level is generate_qa_dataset? +

generate_qa_dataset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit generate_qa_dataset? +

Yes. Add a rate_limit block to the generate_qa_dataset 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 generate_qa_dataset completely? +

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

generate_qa_dataset is provided by the RAGScore MCP server (pypi:ragscore). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.