Run a focused subset: pytest -k <keyword> with JSON report.
AI agents invoke run_tests_focus to trigger actions in Mcp Debugpy. 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 pytest with a keyword filter, which executes Python code. This is an Execute action because it triggers external operations (test execution) whose effects depend on arguments (the keyword filter and underlying test code). While tests are typically benign, an AI agent could be tricked into running malicious test code if it exists in the codebase, or could exhaust resources by running expensive tests.
From the tool's definition Tool description states 'Run a focused subset: pytest -k <keyword>' — this executes pytest, a test runner that executes arbitrary Python code.
Documented attack patterns abuse exactly the kind of access run_tests_focus gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Debugpy, and nothing reaches the server without passing your rules. This is the rule we recommend for run_tests_focus:
{
"version": "1",
"default": "deny",
"tools": {
"run_tests_focus": {
"limits": [
{
"counter": "run_tests_focus_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_tests_focus 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.
Run a focused subset: pytest -k <keyword> with JSON report. It is categorised as a Execute tool in the Mcp Debugpy MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Debugpy MCP server in PolicyLayer and add a rule for run_tests_focus: 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 Mcp Debugpy. Nothing to install.
run_tests_focus 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_focus 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_focus. 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_focus is provided by the Mcp Debugpy MCP server (markomanninen/mcp-debugpy). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Debugpy, 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.
16 Mcp Debugpy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.