v0.9.1 (extended v0.9.2 with auto-discovery) — Walk a plan
AI agents call verify_plan to retrieve information from Mk Qa Master without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to read or traverse a QA plan to validate or inspect its contents. No language suggests creation, modification, deletion, execution of arbitrary code, or financial impact. The low severity reflects minimal blast radius — examining a plan poses negligible risk even if an AI agent misuses it, as it likely only traverses existing data without side effects.
From the tool's definition Tool name 'verify_plan' combined with description 'Walk a plan' indicates traversal/inspection of an existing plan. The verb 'walk' implies reading or traversing data structures without modification.
Documented attack patterns abuse exactly the kind of access verify_plan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mk Qa Master, and nothing reaches the server without passing your rules. This is the rule we recommend for verify_plan:
{
"version": "1",
"default": "deny",
"tools": {
"verify_plan": {}
}
}verify_plan is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
v0.9.1 (extended v0.9.2 with auto-discovery) — Walk a plan. It is categorised as a Read tool in the Mk Qa Master MCP Server, which means it retrieves data without modifying state.
Register the Mk Qa Master MCP server in PolicyLayer and add a rule for verify_plan: 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 Mk Qa Master. Nothing to install.
verify_plan 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_plan 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_plan. 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_plan is provided by the Mk Qa Master MCP server (kao273183/mk-qa-master). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mk Qa Master, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 Mk Qa Master tools catalogued and risk-classified — across an index of 43,000+ MCP servers.