AI agents invoke dap_launch 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.
The dap_launch tool initiates execution of a Python process under debugger control. This is an Execute action—it triggers external operations (running Python code/tests) whose effects depend on arguments (what script/test is launched). While the tool description is empty, the function name and server context make its purpose clear.
From the tool's definition Tool name 'dap_launch' on a Debug Adapter Protocol server for Python debugging; sibling tools include dap_continue, dap_step_in, dap_step_over which are execution control commands. 'Launch' in DAP context means initiating a debugged process.
Documented attack patterns abuse exactly the kind of access dap_launch 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_launch:
{
"version": "1",
"default": "deny",
"tools": {
"dap_launch": {
"limits": [
{
"counter": "dap_launch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}dap_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.
dap_launch. 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_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 Mcp Debugpy. Nothing to install.
dap_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 dap_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 dap_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.
dap_launch 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.