AI agents call qa_get_verification_code 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 verification code data from the database without modifying, deleting, or executing any operations. The explicit 'read-only' designation confirms it performs data retrieval only. The severity is low because reading verification codes has limited blast radius in a QA/testing context, though in production this could be higher if exposed to unauthorized actors.
From the tool's definition Tool description states 'Return the latest email verification code' and explicitly labels it as 'read-only SQL helper', indicating a retrieval operation with no side effects.
Attacks that exploit this kind of access
Return the latest email verification code for a registered user (read-only SQL helper for QA flows). 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_get_verification_code: 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_get_verification_code 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_get_verification_code 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_get_verification_code. 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_get_verification_code 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →