AI agents invoke stop_execution to trigger actions in OpenTester. 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 executes an action that terminates an ongoing process. While not destructive to persistent data, it causes an immediate side effect on a running system operation. The severity is high because stopping an execution could interrupt critical testing workflows or leave systems in an inconsistent state, though the action is technically reversible by restarting the execution.
From the tool's definition Tool name 'stop_execution' and description 'Stop a running execution via FastAPI' indicates the tool triggers an external operation (stopping a process/execution) whose effects depend on which execution is targeted.
Documented attack patterns abuse exactly the kind of access stop_execution gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenTester, and nothing reaches the server without passing your rules. This is the rule we recommend for stop_execution:
{
"version": "1",
"default": "deny",
"tools": {
"stop_execution": {
"limits": [
{
"counter": "stop_execution_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stop_execution 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.
Stop a running execution via FastAPI. It is categorised as a Execute tool in the OpenTester MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenTester MCP server in PolicyLayer and add a rule for stop_execution: 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 OpenTester. Nothing to install.
stop_execution 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 stop_execution 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 stop_execution. 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.
stop_execution is provided by the OpenTester MCP server (kznr02/opentester). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenTester, 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.
23 OpenTester tools catalogued and risk-classified — across an index of 43,000+ MCP servers.