Debug-MCP

Instructions

Implementation Reference

• src/mcp_debug_tool/server.py:373-441 (handler)

  Primary MCP handler for 'sessions_continue' tool. Validates input, calls SessionManager.continue_execution_async, and formats response as JSON.
  async def _handle_sessions_continue(self, arguments: dict) -> list[TextContent]: """ Handler for sessions_continue tool. Continues execution to the next breakpoint. """ try: session_id = arguments.get("sessionId") if not session_id: return [ TextContent( type="text", text=json.dumps({ "error": { "type": "ValueError", "message": "sessionId is required", } }), ) ] request = ContinueRequest( file=arguments["file"], line=arguments["line"], ) # Convert to BreakpointRequest (they have same structure) bp_request = BreakpointRequest( file=request.file, line=request.line, ) response = await self.session_manager.continue_execution_async( session_id, bp_request ) result = response.model_dump() return [ TextContent( type="text", text=json.dumps(result), ) ] except KeyError as e: return [ TextContent( type="text", text=json.dumps({ "error": { "type": "SessionNotFound", "message": str(e), } }), ) ] except Exception as e: logger.exception("Error continuing execution") return [ TextContent( type="text", text=json.dumps({ "error": { "type": type(e).__name__, "message": str(e), } }), ) ]
• src/mcp_debug_tool/server.py:111-133 (registration)

  Tool registration in @server.list_tools(), including name, description, and JSON schema for input validation.
  Tool( name="sessions_continue", description="Continue execution to the next breakpoint", inputSchema={ "type": "object", "properties": { "sessionId": { "type": "string", "description": "The debug session ID", }, "file": { "type": "string", "description": "Project-relative file path", }, "line": { "type": "integer", "description": "Line number (1-based)", "minimum": 1, }, }, "required": ["sessionId", "file", "line"], }, ),
• src/mcp_debug_tool/schemas.py:70-74 (schema)

  Pydantic model ContinueRequest used in handler for input validation (matches MCP inputSchema).
  class ContinueRequest(BaseModel): """Request to continue to next breakpoint.""" file: str = Field(..., description="Project-relative path to file") line: int = Field(..., ge=1, description="1-based line number")
• src/mcp_debug_tool/sessions.py:495-534 (helper)

  Core continue_execution logic in SessionManager: validates state, dispatches to DAP or legacy BDB implementation.
  def continue_execution( self, session_id: str, request: BreakpointRequest ) -> BreakpointResponse: """ Continue execution to next breakpoint within same session. Args: session_id: Session ID request: Breakpoint request with file and line Returns: Breakpoint response with locals at next breakpoint Raises: KeyError: If session not found ValueError: If file/line is invalid """ session = self.get_session(session_id) # Validate breakpoint location using session's workspace root breakpoint_path = resolve_workspace_path(session.workspace_root, request.file) validate_file_and_line(breakpoint_path, request.line) # Session must be paused (from previous breakpoint) if session.status != SessionStatus.PAUSED: return BreakpointResponse( hit=False, completed=False, error=ExecutionError( type="InvalidStateError", message=f"Cannot continue from state: {session.status}", ), ) # Use DAP if enabled (default) if session.use_dap: return self._continue_execution_dap(session, breakpoint_path, request.line) else: return self._continue_execution_bdb(session, breakpoint_path, request.line)
• src/mcp_debug_tool/sessions.py:964-972 (helper)

  Async wrapper continue_execution_async called from MCP handler.
  async def continue_execution_async( self, session_id: str, request: BreakpointRequest ) -> BreakpointResponse: """ Async wrapper for continue_execution. Runs the synchronous continue_execution in a thread pool to avoid blocking. """ return await asyncio.to_thread(self.continue_execution, session_id, request)