This record as markdown: /tools/airmang-hwpx-mcp-server/verify-question-splits.md
What verify_question_splits does on Hwpx
AI agents call verify_question_splits to retrieve information from Hwpx without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why verify_question_splits is rated Low
The tool name 'verify_question_splits' most naturally suggests checking or validating the state of question splits within a document, which would be a read operation. Without a description, we cannot confirm it performs side effects. The sibling tools show a clear pattern of modification operations (add_*, analyze_*), but this tool's 'verify' prefix suggests it queries or inspects rather than modifies.
From the tool's definition Tool name 'verify_question_splits' combined with empty description suggests a verification/analysis operation. In context of document processing, verification typically involves examining or querying document state without modification.
Attacks that exploit this kind of access
The rule that runs verify_question_splits safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Hwpx, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For verify_question_splits, this is the rule to start with:
verify_question_splits is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Hwpx, apply this rule, and every verify_question_splits call is checked against it from then on.
Questions about verify_question_splits
verify_question_splits is a read tool on the Hwpx MCP server. It is categorised as a Read tool in the Hwpx MCP Server, which means it retrieves data without modifying state.
Register the Hwpx MCP server in PolicyLayer and add a rule for verify_question_splits: 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 Hwpx. Nothing to install.
verify_question_splits is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the verify_question_splits 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 verify_question_splits. 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.
verify_question_splits is provided by the Hwpx MCP server (airmang/hwpx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Hwpx, and thousands of servers like it.
This server
Across the catalogue