AI agents invoke run_failed to trigger actions in Mk Qa Master. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers execution of arbitrary test code whose behavior and side effects depend entirely on test implementation. While tests are typically designed to be safe, a malicious or buggy test could perform destructive actions (delete files, modify databases, make API calls, etc.).
From the tool's definition Tool runs tests (specifically failed tests): 'run_failed' executes test suites via the mcp-test-runner server, which supports pytest, Jest, Cypress, Go, and Maestro frameworks. Description indicates it re-runs previously failed tests.
Documented attack patterns abuse exactly the kind of access run_failed 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 run_failed:
{
"version": "1",
"default": "deny",
"tools": {
"run_failed": {
"limits": [
{
"counter": "run_failed_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_failed stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
只重跑上次失敗的測試——比跑整套套件快很多，適合修完一個 bug 後驗證迭代。. It is categorised as a Execute tool in the Mk Qa Master MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mk Qa Master MCP server in PolicyLayer and add a rule for run_failed: 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.
run_failed is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_failed 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 run_failed. 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.
run_failed 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.