AI agents call qa_list_recent_users to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries data without modifying it. It lists users matching a filter (email prefix) but does not create, modify, delete, or execute external operations. The explicit 'read-only' annotation confirms it is a Read operation with minimal blast radius.
From the tool's definition Tool name 'qa_list_recent_users' and description explicitly states 'read-only SQL helper' and 'List recently created users'. The description emphasizes read-only nature and no side effects.
Attacks that exploit this kind of access
List recently created users matching an email prefix (read-only SQL helper for QA cleanup/review). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for qa_list_recent_users: 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. Nothing to install.
qa_list_recent_users 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 qa_list_recent_users 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 qa_list_recent_users. 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.
qa_list_recent_users is provided by the MCP server (victormyschik/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
qa_list_recent_users is one line of 's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →