AI agents invoke run_tests to trigger actions in Carrot AI PM. 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.
Running tests executes code whose effects depend on test implementation and environment state. This is Execute (not Read) because it triggers operations beyond simple retrieval. Severity is medium rather than high because test execution is generally bounded to non-production environments with reversible side effects (test databases, logs, artifacts).
From the tool's definition Tool name 'run_tests' indicates execution of test suites. Empty description limits certainty but context of spec-driven development tool for AI coding assistants suggests this triggers automated test execution.
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 Carrot AI PM, 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.
run_tests. It is categorised as a Execute tool in the Carrot AI PM MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Carrot AI PM 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 Carrot AI PM. 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 Carrot AI PM MCP server (talvinder/carrot-ai-pm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Carrot AI PM tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Carrot AI PM tools catalogued and risk-classified — across an index of 42,500+ MCP servers.