AI agents invoke run_local_tests to trigger actions in Interactive Leetcode. 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 with effects dependent on the code being tested. While not as severe as running unrestricted shell commands, executing local tests can consume resources, modify local state, or expose sensitive information through test output. It is Execute rather than Write because it runs code rather than merely storing data.
From the tool's definition Tool name 'run_local_tests' and description prefix 'Runs the user' indicates execution of code/tests locally.
Documented attack patterns abuse exactly the kind of access run_local_tests gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Interactive Leetcode, and nothing reaches the server without passing your rules. This is the rule we recommend for run_local_tests:
{
"version": "1",
"default": "deny",
"tools": {
"run_local_tests": {
"limits": [
{
"counter": "run_local_tests_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_local_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.
Runs the user. It is categorised as a Execute tool in the Interactive Leetcode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Interactive Leetcode MCP server in PolicyLayer and add a rule for run_local_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 Interactive Leetcode. Nothing to install.
run_local_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_local_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_local_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_local_tests is provided by the Interactive Leetcode MCP server (@sperekrestova/interactive-leetcode-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Interactive Leetcode, 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 Interactive Leetcode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.