dap-mcp is a server implementation that bridges debugging tools with AI systems through the Debug Adapter Protocol (DAP). It enables AI assistants to control debuggers, set breakpoints, step through code, evaluate expressions, and inspect variables - all through standardized MCP tools. The server supports multiple debugging backends (currently debugpy) and renders debugging information in XML format for easy consumption by LLMs, making it particularly valuable for AI-assisted debugging workflows where context about program state needs to be maintained throughout a conversation.
No reviews yet. Be the first to review!
Sign in to join the conversation
Highlight AILaunch the debuggee program.
Set a breakpoint at a specified file and line (with an optional condition).
Remove a breakpoint from a specified file and line.
List all breakpoints currently set in the debugger.
Continue program execution after hitting a breakpoint.
Step into a function call.
Step out of the current function.
Step over to the next line of code.
Evaluate an expression in the current debugging context.
Switch to a different stack frame.
View source code around a specified line (using the last provided file if none is specified).
Terminate the debugging session.
