AI agents invoke step_out to trigger actions in DebugMCP. 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 directly controls the execution of code by manipulating the call stack and resuming program execution until the current function returns. While individual step operations are relatively low-risk in a debugging context, the ability to control execution flow across multiple languages could be misused by an agent to manipulate program behavior in unpredictable ways.
From the tool's definition The tool 'step_out' is part of a debugging interface that controls code execution flow. It steps out of the current function, which is a form of executing and controlling program behavior.
Documented attack patterns abuse exactly the kind of access step_out gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DebugMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for step_out:
{
"version": "1",
"default": "deny",
"tools": {
"step_out": {
"limits": [
{
"counter": "step_out_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}step_out 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.
Step out of the current function. It is categorised as a Execute tool in the DebugMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Debug MCP server in PolicyLayer and add a rule for step_out: 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 DebugMCP. Nothing to install.
step_out 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 step_out 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 step_out. 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.
step_out is provided by the Debug MCP server (microsoft/debugmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DebugMCP, 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.
13 DebugMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.