Return the breakpoints most recently registered with the adapter.
AI agents call dap_list_breakpoints to retrieve information from Mcp Debugpy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves debugging information (breakpoint list) from the debugpy adapter. It performs no mutations, executions, or side effects—it only queries and returns existing breakpoint data. While it's part of a debugging system that can execute code, this specific tool is purely informational. Risk is low as it cannot directly harm systems or data.
From the tool's definition Tool name 'dap_list_breakpoints' and description 'Return the breakpoints most recently registered with the adapter' indicate a query operation that retrieves state without modifying it.
Documented attack patterns abuse exactly the kind of access dap_list_breakpoints 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_list_breakpoints:
{
"version": "1",
"default": "deny",
"tools": {
"dap_list_breakpoints": {}
}
}dap_list_breakpoints is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Return the breakpoints most recently registered with the adapter. It is categorised as a Read tool in the Mcp Debugpy MCP Server, which means it retrieves data without modifying state.
Register the Mcp Debugpy MCP server in PolicyLayer and add a rule for dap_list_breakpoints: 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_list_breakpoints is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the dap_list_breakpoints 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_list_breakpoints. 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_list_breakpoints 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.