AI agents call get_qa_context 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 reads QA knowledge documentation (business rules, historical bugs, standard assertions) from a markdown file. It is a pure data retrieval operation with no side effects, modifications, or external command execution. The low severity reflects that it only accesses project metadata and documentation, which carries minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_qa_context' and description fragment '讀取受測專案的 qa-knowledge.md' (reads the project's qa-knowledge.md) indicates retrieval of documentation/metadata without modification.
Documented attack patterns abuse exactly the kind of access get_qa_context 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 get_qa_context:
{
"version": "1",
"default": "deny",
"tools": {
"get_qa_context": {}
}
}get_qa_context 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.
讀取受測專案的 qa-knowledge.md（業務規則 / 歷史 Bug / 標準斷言文字 /. 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 get_qa_context: 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.
get_qa_context 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 get_qa_context 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 get_qa_context. 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.
get_qa_context 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.