Execute the current line of code without diving into it.
AI agents invoke step_over 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.
step_over executes code statements as part of debugger control flow. While it doesn't run arbitrary user-supplied code directly, it progresses execution of the target program, which qualifies as Execute category. Severity is high because misuse (e.g., stepping through a program that deletes files or makes network calls) could trigger unintended side effects depending on what code the debugged program contains.
From the tool's definition Tool description states 'Execute the current line of code' — this directly runs code execution during debugging sessions. The broader server context confirms this is a debugging interface that controls program execution flow across multiple languages.
Documented attack patterns abuse exactly the kind of access step_over 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_over:
{
"version": "1",
"default": "deny",
"tools": {
"step_over": {
"limits": [
{
"counter": "step_over_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}step_over 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.
Execute the current line of code without diving into it. 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_over: 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_over 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_over 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_over. 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_over 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.