Step out of the current function on the active thread.
AI agents invoke dap_step_out 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.
While a single step operation appears localized, it executes control flow changes that affect running program behavior. Combined with the server's ability to launch processes (dap_launch), continue execution (dap_continue), and run tests, this tool enables triggering arbitrary code execution paths. An AI agent could use step commands in sequence to execute unintended code branches or manipulate program behavior.
From the tool's definition The tool 'dap_step_out' is described as stepping out of the current function on the active thread. This is a debugger control operation that alters program execution flow.
Documented attack patterns abuse exactly the kind of access dap_step_out 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 dap_step_out:
{
"version": "1",
"default": "deny",
"tools": {
"dap_step_out": {
"limits": [
{
"counter": "dap_step_out_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}dap_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 on the active thread. 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 dap_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 Mcp Debugpy. Nothing to install.
dap_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 dap_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 dap_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.
dap_step_out 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.