Resume program execution until the next breakpoint is hit or the program completes.
AI agents invoke continue_execution 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 executes code (the debugged program) by resuming its execution. While the execution is limited to a program already running in a controlled debugging environment, it still constitutes an Execute action because it triggers external operations whose effects depend on the program's behavior.
From the tool's definition continue_execution resumes program execution, which is an external operation that triggers code to run. The tool enables the debugger to execute arbitrary code within the debugging context.
Documented attack patterns abuse exactly the kind of access continue_execution 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 continue_execution:
{
"version": "1",
"default": "deny",
"tools": {
"continue_execution": {
"limits": [
{
"counter": "continue_execution_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}continue_execution 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.
Resume program execution until the next breakpoint is hit or the program completes. 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 continue_execution: 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.
continue_execution 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 continue_execution 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 continue_execution. 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.
continue_execution 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.