Launch the debuggee program. Set breakpoints before launching if necessary.
AI agents invoke launch to trigger actions in Dap. 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.
Launching a debuggee program is an execute action that triggers external code execution. While not destructive by itself, it has significant blast radius: an AI agent could launch malicious programs, crash systems, or trigger unintended side effects. This is classified as Execute rather than Destructive because launching itself is not irreversible, though the launched program's effects might be.
From the tool's definition Tool description states 'Launch the debuggee program', which initiates execution of external code/processes. The server's purpose is to 'control debuggers' and 'navigate source code during debugging sessions', confirming this tool triggers program execution.
Documented attack patterns abuse exactly the kind of access launch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dap, and nothing reaches the server without passing your rules. This is the rule we recommend for launch:
{
"version": "1",
"default": "deny",
"tools": {
"launch": {
"limits": [
{
"counter": "launch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}launch 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.
Launch the debuggee program. Set breakpoints before launching if necessary. It is categorised as a Execute tool in the Dap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dap MCP server in PolicyLayer and add a rule for launch: 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 Dap. Nothing to install.
launch 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 launch 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 launch. 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.
launch is provided by the Dap MCP server (kashuncheng/dap_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dap, 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.
14 Dap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.