AI agents invoke run-tests to trigger actions in VibeCoding System. 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 runs test code, which is a form of code execution (Execute category). Severity is medium because test execution is a normal development operation with contained scope (tests target the codebase), but misuse could still run arbitrary test code or access test data. It's not Read (test suites create side effects like state changes), not Destructive (tests are reversible), not Financial.
From the tool's definition Tool description states 'Execute test suites' — the verb 'Execute' directly indicates running code/scripts. Test suites involve arbitrary code execution whose outcomes depend on test contents and environment state.
Documented attack patterns abuse exactly the kind of access run-tests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VibeCoding System, and nothing reaches the server without passing your rules. This is the rule we recommend for run-tests:
{
"version": "1",
"default": "deny",
"tools": {
"run-tests": {
"limits": [
{
"counter": "run-tests_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run-tests 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.
Execute test suites and return detailed results. It is categorised as a Execute tool in the VibeCoding System MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VibeCoding System MCP server in PolicyLayer and add a rule for run-tests: 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 VibeCoding System. Nothing to install.
run-tests 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-tests 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-tests. 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-tests is provided by the VibeCoding System MCP server (zenobia000/vibecoding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VibeCoding System, 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.
24 VibeCoding System tools catalogued and risk-classified — across an index of 43,000+ MCP servers.